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

    Neuronpedia

    INDEX
    Explanations

    Programming code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phen
    -0.06
    dyn
    -0.06
    ệc
    -0.06
    .photo
    -0.06
     sơ
    -0.06
    _OLD
    -0.06
    導
    -0.06
    ール
    -0.06
     hieronta
    -0.06
    醨
    -0.06
    POSITIVE LOGITS
    -bind
    0.07
     peers
    0.07
    _rsp
    0.07
    紧张
    0.07
    Important
    0.06
     impro
    0.06
    资助
    0.06
    储蓄
    0.06
    consum
    0.06
     discrim
    0.06
    Act Density 0.014%

    No Known Activations