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

    Neuronpedia

    INDEX
    Explanations

    dystopian futures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verse
    -0.08
     boxing
    -0.07
    excerpt
    -0.07
     Actress
    -0.07
    exist
    -0.07
    -vis
    -0.07
     Canton
    -0.06
     group
    -0.06
     gp
    -0.06
    뼝
    -0.06
    POSITIVE LOGITS
    🦖
    0.07
    (--
    0.07
     JTextField
    0.07
    _TRY
    0.07
    .UnitTesting
    0.07
    ורות
    0.07
    战略
    0.06
     controllers
    0.06
    .JSONException
    0.06
     функци
    0.06
    Act Density 0.272%

    No Known Activations