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

    Neuronpedia

    INDEX
    Explanations

    described/previously

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (arr
    -0.07
    .parseLong
    -0.07
    umption
    -0.06
    _PIX
    -0.06
    �
    -0.06
    _bit
    -0.06
     المح
    -0.06
     barbar
    -0.06
    แท
    -0.06
    eps
    -0.06
    POSITIVE LOGITS
     None
    0.06
    รง
    0.06
     dislike
    0.06
    іно
    0.06
     LETTER
    0.06
    were
    0.06
     journals
    0.06
    tryside
    0.06
     %↵
    0.06
     ；
    0.06
    Act Density 0.005%

    No Known Activations