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

    Neuronpedia

    INDEX
    Explanations

    physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -quarter
    -0.07
    ridden
    -0.07
     Phill
    -0.07
     condemning
    -0.06
    regular
    -0.06
    ات
    -0.06
    Regular
    -0.06
    NSUInteger
    -0.06
    PLUS
    -0.06
    ubern
    -0.06
    POSITIVE LOGITS
    　ゝ
    0.06
     میل
    0.06
    inya
    0.06
    neas
    0.06
    d
    0.05
     Schw
    0.05
     reinst
    0.05
    shield
    0.05
    .codes
    0.05
    .hand
    0.05
    Act Density 0.089%

    No Known Activations