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

    Neuronpedia

    INDEX
    Explanations

    generic programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gọn
    -0.07
    reib
    -0.06
    `:
    -0.06
    -growing
    -0.06
     cherche
    -0.06
    щее
    -0.06
    )!
    -0.06
     закры
    -0.06
    elm
    -0.06
    [:]
    -0.06
    POSITIVE LOGITS
    _hero
    0.07
     signer
    0.06
     Churchill
    0.06
    assume
    0.06
    ,max
    0.06
    .kode
    0.06
    akat
    0.06
     futuro
    0.06
     halk
    0.06
    _verified
    0.06
    Act Density 0.082%

    No Known Activations