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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate existence or presence of elements in a discussion or description

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

    -ing after verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſehen
    -0.73
    出版年
    -0.73
     témoig
    -0.70
    DoubleQuotes
    -0.67
     indígen
    -0.66
     müſſen
    -0.66
     ſever
    -0.65
    ſicht
    -0.63
     Waſſer
    -0.63
     ſeine
    -0.63
    POSITIVE LOGITS
     being
    0.41
     To
    0.36
     support
    0.36
     resolve
    0.36
    სქოლიო
    0.35
     пола
    0.35
     imp
    0.35
     who
    0.34
     destek
    0.34
     seeing
    0.34
    Act Density 0.093%

    No Known Activations