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

    Neuronpedia

    INDEX
    Explanations

    Court appeals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Failed
    -0.08
     outliers
    -0.08
    .getTag
    -0.07
     pii
    -0.07
    ∣
    -0.07
    醚
    -0.07
     styleUrls
    -0.07
    UIStoryboardSegue
    -0.07
    Ă
    -0.07
    Indent
    -0.07
    POSITIVE LOGITS
    With
    0.07
     Cald
    0.07
    ᵏ
    0.07
     makers
    0.07
     Rogers
    0.06
    介绍说
    0.06
    なお
    0.06
    _CRITICAL
    0.06
    开着
    0.06
    한다는
    0.06
    Act Density 0.002%

    No Known Activations