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

    Neuronpedia

    INDEX
    Explanations

    033

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paras
    -0.07
    otros
    -0.06
    .truth
    -0.06
    ologies
    -0.06
    logo
    -0.06
    pv
    -0.06
    .readFile
    -0.06
    SITE
    -0.06
     المو
    -0.06
    Explorer
    -0.06
    POSITIVE LOGITS
     ################
    0.06
    ｣
    0.06
     bounding
    0.06
     стос
    0.06
    发送
    0.06
     deprivation
    0.06
     fades
    0.06
     PRINT
    0.06
    £o
    0.06
    APTER
    0.06
    Act Density 0.002%

    No Known Activations