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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _rule
    -0.08
    _rate
    -0.07
    +",
    -0.07
    387
    -0.06
     USD
    -0.06
     Collective
    -0.06
     offenses
    -0.06
     practices
    -0.06
     Mùa
    -0.06
    _upload
    -0.06
    POSITIVE LOGITS
    気
    0.06
    obra
    0.06
    imax
    0.06
     Syrians
    0.06
     licz
    0.06
    phe
    0.06
     jsonObj
    0.06
    té
    0.06
    luck
    0.06
     kube
    0.06
    Act Density 0.108%

    No Known Activations