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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Return
    -0.07
    Balancer
    -0.06
    仅
    -0.06
    Detector
    -0.06
    )，
    -0.06
     <<↵
    -0.06
     &,
    -0.06
    spam
    -0.06
     jihad
    -0.06
    ন
    -0.06
    POSITIVE LOGITS
    شماری
    0.06
     Національ
    0.06
    <hr
    0.06
     kms
    0.06
    0.06
     Cognitive
    0.06
     玩家
    0.06
     iov
    0.06
     homem
    0.06
    _sim
    0.06
    Act Density 0.145%

    No Known Activations