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

    Neuronpedia

    INDEX
    Explanations

    Scientific nomenclature and taxonomy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (method
    -0.08
    生活的
    -0.07
     회원
    -0.07
    ("#{
    -0.07
    鳇
    -0.07
    ên
    -0.07
    VIN
    -0.07
    东方财富
    -0.07
    แผน
    -0.07
    лен
    -0.07
    POSITIVE LOGITS
     güvenlik
    0.08
     alternatives
    0.07
     reading
    0.07
     Fifty
    0.07
    rch
    0.07
     feels
    0.07
    epochs
    0.07
    荭
    0.07
    퀅
    0.07
     Frame
    0.06
    Act Density 0.244%

    No Known Activations