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

    Neuronpedia

    INDEX
    Explanations

    movies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mix
    -0.07
    MH
    -0.06
    Ka
    -0.06
     Ka
    -0.06
     nemá
    -0.06
    ixe
    -0.06
     Pokémon
    -0.06
    ké
    -0.06
    issa
    -0.06
     Woo
    -0.06
    POSITIVE LOGITS
     ekonom
    0.07
    (EXIT
    0.07
    ONSE
    0.06
    TRGL
    0.06
     phil
    0.06
    _cpu
    0.06
     позвол
    0.06
    -gray
    0.06
    _Request
    0.06
     letters
    0.06
    Act Density 0.113%

    No Known Activations