Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    complex sentence structures and nuanced expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes after "while it" or "though it"

    np_acts-logits-general · gemini-2.0-flash

    concessive clauses, hypothetical, or qualified statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Either
    -0.96
     Either
    -0.91
    either
    -0.86
     either
    -0.84
     even
    -0.77
    UnusedPrivate
    -0.77
    更是
    -0.74
     nämlich
    -0.71
     entweder
    -0.71
    even
    -0.71
    POSITIVE LOGITS
     technically
    1.38
     nominally
    1.26
     initially
    1.16
     outwardly
    1.14
     ostensibly
    1.10
     superfic
    1.10
     theoretically
    1.03
     admittedly
    1.00
     téc
    0.95
     inicialmente
    0.93
    Act Density 0.511%

    No Known Activations