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

    Neuronpedia

    INDEX
    Explanations

    validate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fem
    -0.07
    .party
    -0.07
     digits
    -0.07
    ajor
    -0.07
    .histogram
    -0.06
    Script
    -0.06
    .REQUEST
    -0.06
    /color
    -0.06
    >this
    -0.06
    .WEST
    -0.06
    POSITIVE LOGITS
    เด
    0.07
     χρησιμοποι
    0.06
     di
    0.06
     acknowledgment
    0.06
    死
    0.06
    Print
    0.06
    ULK
    0.06
     presenting
    0.06
     Bij
    0.06
     عزیز
    0.06
    Act Density 0.002%

    No Known Activations