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

    Neuronpedia

    INDEX
    Explanations

    combined

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (sin
    -0.08
    (kv
    -0.07
    ...(
    -0.07
     เมษายน
    -0.07
     domingo
    -0.07
    (F
    -0.07
     sectarian
    -0.07
    يمي
    -0.07
    (d
    -0.07
     совершен
    -0.06
    POSITIVE LOGITS
     borderBottom
    0.08
    uba
    0.08
    .concurrent
    0.07
    掐
    0.07
    ask
    0.07
    ="";
↵
    0.07
    low
    0.07
    梳
    0.07
    አ
    0.07
     sliders
    0.07
    Act Density 0.021%

    No Known Activations