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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    can
    -0.07
     pf
    -0.07
    OUND
    -0.06
     Scal
    -0.06
    Su
    -0.06
     TEST
    -0.06
     tv
    -0.06
    TRAIN
    -0.06
     Cour
    -0.06
    ArgsConstructor
    -0.06
    POSITIVE LOGITS
     navigationOptions
    0.07
     cipher
    0.07
     AnyObject
    0.07
     *----------------------------------------------------------------
    0.06
     зависим
    0.06
    blocking
    0.06
     руках
    0.06
    سازی
    0.06
    ."]
    0.06
     YYS
    0.06
    Act Density 0.015%

    No Known Activations