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

    Neuronpedia

    INDEX
    Explanations

    color

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Unix
    -0.07
     참가
    -0.06
     prefixes
    -0.06
    adx
    -0.06
     progressives
    -0.06
    hawks
    -0.06
    unbind
    -0.06
     Jugend
    -0.06
     bekom
    -0.06
     basePath
    -0.06
    POSITIVE LOGITS
     paed
    0.07
     Traff
    0.07
    #
↵
    0.06
    Usually
    0.06
    Normally
    0.06
     Increment
    0.06
    ์ช
    0.06
     GraphQL
    0.06
     Jane
    0.06
    celik
    0.06
    Act Density 0.002%

    No Known Activations