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

    Neuronpedia

    INDEX
    Explanations

    Code, files, or errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    haps
    -0.07
    Brown
    -0.07
     cuent
    -0.06
     Cop
    -0.06
     Bread
    -0.06
     Ar
    -0.06
    FACT
    -0.06
    Sites
    -0.06
    PushButton
    -0.06
    Ar
    -0.06
    POSITIVE LOGITS
    toBeTruthy
    0.07
    (val
    0.07
    _vectors
    0.06
     kube
    0.06
    _filepath
    0.06
    	Value
    0.06
    (nameof
    0.06
    ,double
    0.06
    ί
    0.06
    (hWnd
    0.06
    Act Density 0.000%

    No Known Activations