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

    Neuronpedia

    INDEX
    Explanations

    mo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arov
    -0.07
     Karn
    -0.07
    _card
    -0.07
    set
    -0.07
    .setup
    -0.07
    shell
    -0.07
    LOOP
    -0.07
    (set
    -0.07
    Serializer
    -0.06
    Gs
    -0.06
    POSITIVE LOGITS
     mo
    0.09
     prostituer
    0.07
     mor
    0.07
    mo
    0.07
    navigator
    0.07
     Дмит
    0.07
     tendencies
    0.07
     во
    0.06
     Amerikan
    0.06
     additives
    0.06
    Act Density 0.003%

    No Known Activations