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

    Neuronpedia

    INDEX
    Explanations

    Code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کو
    -0.07
    isper
    -0.07
    Attempting
    -0.07
     longest
    -0.06
    .sort
    -0.06
     onBindViewHolder
    -0.06
     eas
    -0.06
     accumulator
    -0.06
    _'+
    -0.06
    .Once
    -0.06
    POSITIVE LOGITS
    회사
    0.06
    (login
    0.06
    .shiro
    0.06
    graded
    0.06
    omens
    0.06
     dönüş
    0.06
    Suggestions
    0.06
    大的
    0.06
    _tf
    0.06
     živ
    0.06
    Act Density 0.074%

    No Known Activations