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

    Neuronpedia

    INDEX
    Explanations

    technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    私自
    -0.07
    <iostream
    -0.07
    <>();↵
    -0.07
     Ort
    -0.06
    솟
    -0.06
    arde
    -0.06
    _CSV
    -0.06
     ancient
    -0.06
    (Collider
    -0.06
    .rest
    -0.06
    POSITIVE LOGITS
     italiana
    0.08
    _DIRECTORY
    0.07
    "is
    0.07
    防
    0.07
    バス
    0.07
    *z
    0.07
    iare
    0.06
     unsus
    0.06
    -horizontal
    0.06
     FIN
    0.06
    Act Density 0.001%

    No Known Activations