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

    Neuronpedia

    INDEX
    Explanations

    Instruments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RCS
    -0.07
     muddy
    -0.07
    ularity
    -0.06
    SEQU
    -0.06
     excl
    -0.06
    	frame
    -0.06
    UNCT
    -0.06
    CTR
    -0.06
    OCK
    -0.06
     tur
    -0.06
    POSITIVE LOGITS
     tipos
    0.08
    利
    0.07
    imin
    0.07
     Δι
    0.07
    ใช
    0.07
    .optional
    0.07
    Ion
    0.07
    custom
    0.07
    корист
    0.07
     Bij
    0.07
    Act Density 0.001%

    No Known Activations