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

    Neuronpedia

    INDEX
    Explanations

    films

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (front
    -0.07
    packing
    -0.07
    뺨
    -0.07
     nut
    -0.06
    ={`
    -0.06
    פורסם
    -0.06
    不算
    -0.06
     fucks
    -0.06
     knobs
    -0.06
    -nil
    -0.06
    POSITIVE LOGITS
    严重的
    0.08
    ooled
    0.08
     colonies
    0.08
     alg
    0.07
    лем
    0.07
    .house
    0.07
    ㉱
    0.07
    Enterprise
    0.07
    sız
    0.07
    (ic
    0.07
    Act Density 0.005%

    No Known Activations