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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and auxiliary verbs in conversational sentences

    oai_token-act-pair · gemini-2.0-flash

    Expressing sentiments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+
    -0.73
     linkovi
    -0.67
     autorytatywna
    -0.65
    ClientSize
    -0.63
     is
    -0.63
     sort
    -0.62
     defaultstate
    -0.61
    rawDesc
    -0.61
    quite
    -0.58
     StyleSheet
    -0.57
    POSITIVE LOGITS
     itſelf
    0.63
     myſelf
    0.61
     Reſ
    0.60
    forChild
    0.60
     nød
    0.57
     Majefty
    0.56
     themſelves
    0.53
     ſtate
    0.53
     againſt
    0.52
     himſelf
    0.52
    Act Density 11.111%

    No Known Activations