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

    Neuronpedia

    INDEX
    Explanations

    "call it" examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سفر
    -0.08
     adress
    -0.07
     State
    -0.07
    бі
    -0.07
    シ
    -0.06
    ·
    -0.06
    ід
    -0.06
    State
    -0.06
    сте
    -0.06
    ترین
    -0.06
    POSITIVE LOGITS
     fyz
    0.06
    .timing
    0.06
     inauguration
    0.06
     Agility
    0.06
     Gina
    0.06
    idepress
    0.06
    AttribPointer
    0.06
    (alpha
    0.06
    oenix
    0.06
    _BTN
    0.06
    Act Density 0.068%

    No Known Activations