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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    definition
    -0.07
     breakthrough
    -0.06
     ruled
    -0.06
     forgiven
    -0.06
     अत
    -0.06
    benh
    -0.06
     hizo
    -0.06
     zosta
    -0.06
     DF
    -0.06
     admitted
    -0.06
    POSITIVE LOGITS
    .GetType
    0.07
    .configure
    0.07
     připoj
    0.06
    (userData
    0.06
     tagging
    0.06
     Brow
    0.06
     upgrade
    0.06
    ropy
    0.06
     attached
    0.06
    _uv
    0.06
    Act Density 0.041%

    No Known Activations