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

    Neuronpedia

    INDEX
    Explanations

    $$

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muchas
    -0.07
    ‌دان
    -0.07
    _fsm
    -0.07
     grandfather
    -0.07
     kittens
    -0.06
     ری
    -0.06
    uman
    -0.06
     lean
    -0.06
    ifie
    -0.06
    lardı
    -0.06
    POSITIVE LOGITS
    608
    0.07
    643
    0.07
     NGX
    0.06
    0.06
     професій
    0.06
     ((
    0.06
    211
    0.06
    +</
    0.06
    .snapshot
    0.06
     Shot
    0.06
    Act Density 0.008%

    No Known Activations