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

    Neuronpedia

    INDEX
    Explanations

    programming parameters/arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tec
    -0.08
     Méd
    -0.07
     chambers
    -0.07
     chamber
    -0.07
     ฟ
    -0.06
     prisons
    -0.06
     discriminator
    -0.06
     همسر
    -0.06
     disqualified
    -0.06
    ircraft
    -0.06
    POSITIVE LOGITS
    Persistent
    0.07
     danh
    0.07
    ubit
    0.06
     меропри
    0.06
    _MI
    0.06
    バー
    0.06
    σταση
    0.06
     خم
    0.06
    .''
    0.06
    ическим
    0.06
    Act Density 0.032%

    No Known Activations