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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ean
    -1.52
    jang
    -1.16
    hazi
    -0.79
    emption
    -0.54
    eea
    -0.54
    EAN
    -0.53
     qualified
    -0.52
     createState
    -0.52
    Capp
    -0.52
     خارجية
    -0.51
    POSITIVE LOGITS
    sohn
    0.60
    bledon
    0.59
    ThroughAttribute
    0.57
     getInstance
    0.57
    期刊论文
    0.57
     '@/
    0.54
    UnknownFieldSet
    0.54
     Circumstances
    0.53
     trif
    0.52
     Ngb
    0.52
    Act Density 0.070%

    No Known Activations