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

    Neuronpedia

    INDEX
    Explanations

    true if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Thomas
    -0.85
     Tomé
    -0.78
    ctp
    -0.77
    首次
    -0.77
     Thomas
    -0.74
    EnumType
    -0.74
    +="
    -0.74
    Tu
    -0.73
    قبل
    -0.72
    uillez
    -0.71
    POSITIVE LOGITS
    demon
    0.85
    stru
    0.84
    URBANA
    0.81
    despite
    0.79
    Transkrypt
    0.78
    ྄
    0.75
    orb
    0.74
    ywna
    0.74
    pecies
    0.73
    Transcriptie
    0.73
    Act Density 0.041%

    No Known Activations