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

    Neuronpedia

    INDEX
    Explanations

    Small percentages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Wh
    -0.09
    .tagName
    -0.08
    ());
    -0.08
     ){
    -0.07
    apellido
    -0.07
    ellido
    -0.07
    缦
    -0.07
    ：</
    -0.07
     ministry
    -0.07
    (MouseEvent
    -0.07
    POSITIVE LOGITS
    ตล
    0.07
    orphic
    0.07
    urate
    0.07
    世俗
    0.07
    ⲣ
    0.07
    getC
    0.07
    (actions
    0.07
    心底
    0.07
     לבדוק
    0.07
    _imp
    0.06
    Act Density 0.108%

    No Known Activations