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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inne
    -0.07
     وسی
    -0.06
     가까
    -0.06
    자기
    -0.06
    イド
    -0.06
    樂
    -0.06
    Compose
    -0.06
     kak
    -0.06
    ResourceId
    -0.06
     operated
    -0.05
    POSITIVE LOGITS
    .station
    0.07
     erect
    0.06
     ajout
    0.06
     ampl
    0.06
     surv
    0.06
     εξ
    0.06
    zia
    0.06
     Wr
    0.06
    _src
    0.06
     ξ
    0.06
    Act Density 0.402%

    No Known Activations