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

    Neuronpedia

    INDEX
    Explanations

    Documentation/Instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ripple
    -0.06
    igmat
    -0.06
    _sigma
    -0.06
    uplicate
    -0.06
     Bernard
    -0.06
     balls
    -0.06
    cessive
    -0.06
     civilized
    -0.06
    amination
    -0.06
    ์
    -0.06
    POSITIVE LOGITS
    SEMB
    0.07
    (hidden
    0.06
     silenced
    0.06
    dateFormat
    0.06
    Making
    0.06
    ानसभ
    0.06
    stk
    0.06
     sought
    0.06
    'A
    0.06
    _PRINT
    0.06
    Act Density 0.147%

    No Known Activations