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

    Neuronpedia

    INDEX
    Explanations

    country names and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    -1.57
     If
    -1.05
     like
    -0.91
    ENAS
    -0.89
     it
    -0.89
    했다
    -0.86
     right
    -0.86
     hoga
    -0.85
     would
    -0.84
     مثل
    -0.84
    POSITIVE LOGITS
     другом
    1.09
     yyb
    1.05
    atized
    1.05
    ਫ਼
    1.05
    brtc
    1.04
    Ге
    1.00
    1.00
    푼
    0.99
     fapt
    0.99
     grossesse
    0.99
    Act Density 0.000%

    No Known Activations