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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    相关
    -0.07
    _ENABLED
    -0.07
     blanco
    -0.07
     rés
    -0.07
     sanctions
    -0.07
     tercer
    -0.07
     Supplements
    -0.06
    红
    -0.06
     os
    -0.06
    favorite
    -0.06
    POSITIVE LOGITS
     (!(
    0.07
    (form
    0.06
    (!(
    0.06
    ===
    0.06
     guint
    0.06
     Jaime
    0.06
     ===
    0.06
    001
    0.06
    Weapons
    0.06
    teness
    0.06
    Act Density 0.002%

    No Known Activations