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

    Neuronpedia

    INDEX
    Explanations

    references to specific entities or identifiers within a document

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

    numbers and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itself
    -0.35
     even
    -0.33
     and
    -0.30
     yet
    -0.29
     rând
    -0.29
     Even
    -0.29
     although
    -0.28
     μὲν
    -0.28
     term
    -0.28
     alone
    -0.28
    POSITIVE LOGITS
     transfieras
    0.82
    ConstraintMaker
    0.76
    majánló
    0.72
     CreateTagHelper
    0.69
    ſammen
    0.68
    enumii
    0.67
    httphttps
    0.66
     dieſen
    0.65
     queſto
    0.65
     dieſe
    0.65
    Act Density 1.544%

    No Known Activations