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

    Neuronpedia

    INDEX
    Explanations

    code/technical excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AIN
    -0.07
     Geb
    -0.07
     boarded
    -0.07
    .encoder
    -0.07
     WEST
    -0.06
    =S
    -0.06
     feas
    -0.06
    roduction
    -0.06
    aura
    -0.06
    /gen
    -0.06
    POSITIVE LOGITS
    ofi
    0.06
    aversable
    0.06
    mask
    0.06
     rộng
    0.06
     Generated
    0.06
     Internacional
    0.06
     »,
    0.06
    iales
    0.06
    .CreateTable
    0.06
     Shah
    0.06
    Act Density 0.001%

    No Known Activations