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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating legal or regulatory contexts

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

    Punctuation followed by numbers or pronouns

    np_acts-logits-general · gemini-2.0-flash

    start of sentence punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    them
    -0.72
     THEM
    -0.70
    Them
    -0.60
     Them
    -0.58
     herself
    -0.53
     Yourself
    -0.53
     Himself
    -0.52
     henne
    -0.51
     siebie
    -0.51
    eux
    -0.50
    POSITIVE LOGITS
     we
    1.67
     there
    1.65
     they
    1.62
     it
    1.45
     you
    1.33
    there
    1.11
     he
    1.09
     فإن
    1.04
     the
    1.02
     she
    0.97
    Act Density 0.645%

    No Known Activations