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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    스가
    -0.07
    کاران
    -0.07
     seguro
    -0.07
     endurance
    -0.06
     firefox
    -0.06
    immutable
    -0.06
    ourses
    -0.06
     Elvis
    -0.06
     Marcus
    -0.06
    (plugin
    -0.06
    POSITIVE LOGITS
    DEL
    0.06
    еры
    0.06
    Scroll
    0.06
    νο
    0.06
    -derived
    0.06
     fase
    0.06
    REV
    0.06
     graffiti
    0.06
     elif
    0.06
     hiç
    0.06
    Act Density 0.016%

    No Known Activations