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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cent
    -0.07
    .setParent
    -0.07
    ậy
    -0.06
    th
    -0.06
    .firstname
    -0.06
    _half
    -0.06
     нали
    -0.06
    ejs
    -0.06
     spas
    -0.06
     offender
    -0.06
    POSITIVE LOGITS
    рова
    0.07
     (*((
    0.07
    .Or
    0.07
     입니다
    0.06
     выпол
    0.06
     btc
    0.06
    local
    0.06
     pumped
    0.06
    作者
    0.06
    BOOL
    0.06
    Act Density 0.008%

    No Known Activations