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

    Neuronpedia

    INDEX
    Explanations

    file limits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uygu
    -0.06
     Plot
    -0.06
    以上
    -0.06
    Eventually
    -0.06
     punishments
    -0.06
     나오
    -0.06
    انیا
    -0.06
    '])){
    -0.06
     нанес
    -0.06
     Erotik
    -0.06
    POSITIVE LOGITS
    (Me
    0.08
    Obj
    0.07
    ADD
    0.06
    '''↵↵
    0.06
     Obj
    0.06
    .Qu
    0.06
    .add
    0.06
     월
    0.06
     unmist
    0.06
    лення
    0.06
    Act Density 0.011%

    No Known Activations