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

    Neuronpedia

    INDEX
    Explanations

    cancel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __))↵
    -0.07
    identification
    -0.07
    (mapping
    -0.07
    (b
    -0.06
    irket
    -0.06
    charge
    -0.06
     occurrences
    -0.06
     smelled
    -0.06
    Vis
    -0.06
    $pdf
    -0.06
    POSITIVE LOGITS
     INITIAL
    0.07
     redund
    0.06
    Mill
    0.06
     replay
    0.06
    @register
    0.06
     challenger
    0.06
    alculate
    0.06
    栏
    0.06
    shint
    0.06
    /lib
    0.06
    Act Density 0.009%

    No Known Activations