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

    Neuronpedia

    INDEX
    Explanations

    mixture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glaring
    -0.09
     sez
    -0.07
     readers
    -0.07
    _PLAYER
    -0.07
    \ActiveForm
    -0.06
    βάλ
    -0.06
    .Bold
    -0.06
    Credentials
    -0.06
    _radio
    -0.06
    _best
    -0.06
    POSITIVE LOGITS
     mixture
    0.14
    tures
    0.08
    bury
    0.07
    (batch
    0.07
     Tin
    0.07
    ")==
    0.07
     remainder
    0.07
    〔
    0.07
    Incre
    0.06
    ",(
    0.06
    Act Density 0.006%

    No Known Activations