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

    Neuronpedia

    INDEX
    Explanations

    ph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @app
    -0.08
    (name
    -0.07
     loại
    -0.07
    classname
    -0.07
    겊
    -0.06
     thinkers
    -0.06
     fileprivate
    -0.06
    Leader
    -0.06
     Congressional
    -0.06
    늄
    -0.06
    POSITIVE LOGITS
    🚐
    0.07
     wreak
    0.07
    荼
    0.07
    %%%
    0.07
    fieldset
    0.07
    SEM
    0.07
     Gets
    0.07
    ~":"
    0.07
    _INSERT
    0.07
    怕
    0.06
    Act Density 0.060%

    No Known Activations