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

    Neuronpedia

    INDEX
    Explanations

    mentions of officials or spokespersons discussing or declining to disclose information

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

    Followed by "said" after a comma

    np_acts-logits-general · gemini-2.0-flash

    names followed by "said"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.55
    ReusableCell
    -0.48
    argument
    -0.45
    self
    -0.44
    arg
    -0.44
     hunde
    -0.42
    Datuak
    -0.42
    glą
    -0.42
    TextSpan
    -0.41
     svůj
    -0.41
    POSITIVE LOGITS
     zufolge
    0.76
     Theſe
    0.71
    पया
    0.71
     Roskov
    0.71
     himſelf
    0.69
     oversaw
    0.69
     myſelf
    0.67
     selaku
    0.67
     avoient
    0.66
     للاسماء
    0.65
    Act Density 0.156%

    No Known Activations