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

    Neuronpedia

    INDEX
    Explanations

    call include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     masculine
    -0.06
     hạt
    -0.06
     splice
    -0.06
     TOOL
    -0.06
     Stars
    -0.06
     وما
    -0.06
    (bbox
    -0.06
    parate
    -0.06
     UIColor
    -0.06
    ,str
    -0.06
    POSITIVE LOGITS
    Permissions
    0.08
     Emotional
    0.07
    _analysis
    0.07
    Art
    0.07
    ягом
    0.07
    MITTED
    0.07
    930
    0.07
    methods
    0.06
     dünyanın
    0.06
    _EVAL
    0.06
    Act Density 0.006%

    No Known Activations