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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.77
     than
    -0.69
    .
    -0.68
    }'.
    -0.58
    ».
    -0.58
    .'
    -0.57
    .’
    -0.56
    '.
    -0.55
    ’.
    -0.55
    .”
    -0.53
    POSITIVE LOGITS
    ConstraintMaker
    0.68
    digarh
    0.58
    crose
    0.58
    期刊论文
    0.57
    Vidite
    0.56
    ImGui
    0.53
     nahilalakip
    0.51
     pinulongan
    0.50
    enchymal
    0.50
    LookAnd
    0.49
    Act Density 0.002%

    No Known Activations