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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ชาย
    -0.09
     Devils
    -0.09
     แต
    -0.09
    ผิด
    -0.09
     Novo
    -0.08
     ผ
    -0.08
     ลง
    -0.08
    më
    -0.08
     qə
    -0.08
     ദുര
    -0.08
    POSITIVE LOGITS
    609
    0.08
    304
    0.07
    0.07
     distinctly
    0.07
    233
    0.07
    305
    0.07
    333
    0.07
    0.07
    Atom
    0.07
    228
    0.07
    Act Density 0.105%
    No Known Activations