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

    Neuronpedia

    INDEX
    Explanations

    inline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trains
    -0.07
     spheres
    -0.07
    ir
    -0.07
    集中
    -0.06
     sphere
    -0.06
    326
    -0.06
     algebra
    -0.06
     SHIFT
    -0.06
    <|eom_id|>
    -0.06
    ------------
    -0.06
    POSITIVE LOGITS
    듯
    0.07
     urlpatterns
    0.06
     إذ
    0.06
     Inline
    0.06
    osex
    0.06
    _lazy
    0.06
     dishwasher
    0.06
    nish
    0.06
     VB
    0.06
    toUpperCase
    0.06
    Act Density 0.001%

    No Known Activations