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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ReLU
    -0.08
    .apiUrl
    -0.06
     terrorists
    -0.06
     guide
    -0.06
     "*"
    -0.06
    (rec
    -0.06
    _small
    -0.06
     subsidiary
    -0.06
    -extension
    -0.06
    -core
    -0.06
    POSITIVE LOGITS
     dispers
    0.07
     restr
    0.07
     shops
    0.07
     Anch
    0.06
     melt
    0.06
    valu
    0.06
    openid
    0.06
     dö
    0.06
    شاء
    0.06
     unofficial
    0.06
    Act Density 0.053%

    No Known Activations