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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     newcomers
    -0.07
     entityType
    -0.06
     ramp
    -0.06
     vô
    -0.06
    /*
↵
    -0.06
    aw
    -0.06
     독일
    -0.06
     ql
    -0.06
    ppard
    -0.06
     попада
    -0.06
    POSITIVE LOGITS
     ECM
    0.06
    (?:
    0.06
     ORIGINAL
    0.06
     grad
    0.06
    ActiveSheet
    0.06
     coursework
    0.06
    olls
    0.06
    Ey
    0.06
     seri
    0.06
    311
    0.06
    Act Density 0.080%

    No Known Activations