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

    Neuronpedia

    INDEX
    Explanations

    watching TV and movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کل
    -0.07
    _RF
    -0.06
    rozen
    -0.06
     BaseActivity
    -0.06
     века
    -0.06
    ึ
    -0.06
     inmate
    -0.06
     bunker
    -0.06
     obec
    -0.06
    ]+$
    -0.06
    POSITIVE LOGITS
     Clim
    0.07
    .Actions
    0.06
    atron
    0.06
    (['
    0.06
    ←
    0.06
     WP
    0.06
    ná
    0.06
     pleased
    0.06
    \C
    0.06
     getDescription
    0.06
    Act Density 0.061%

    No Known Activations