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

    Neuronpedia

    INDEX
    Explanations

    node or * followed by punctuation/special characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     –
    0.89
    ل
    0.79
     To
    0.77
    पी
    0.77
    ي
    0.75
     AD
    0.74
    ’
    0.71
    ر
    0.71
    기
    0.70
    ari
    0.69
    POSITIVE LOGITS
    catcher
    0.98
    shells
    0.95
     cheques
    0.94
     pessoais
    0.93
     borrar
    0.93
     rashes
    0.91
     surfers
    0.88
    вался
    0.87
    перы
    0.87
     surfer
    0.86
    Act Density 0.002%

    No Known Activations