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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paradise
    -0.08
    ".
    -0.07
    <quote
    -0.07
    _SF
    -0.06
     yazı
    -0.06
    Born
    -0.06
     Executors
    -0.06
    getInt
    -0.06
     isSuccess
    -0.06
    HeaderCode
    -0.06
    POSITIVE LOGITS
    gili
    0.06
    _ASSIGN
    0.06
     lob
    0.06
     обличчя
    0.06
    elsen
    0.06
    SG
    0.06
    -through
    0.06
     nye
    0.06
     znač
    0.06
     mild
    0.06
    Act Density 0.005%

    No Known Activations