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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ึกษ
    -0.07
     trusts
    -0.07
     Workshop
    -0.07
     fak
    -0.06
     Elementary
    -0.06
     Sem
    -0.06
     금액
    -0.06
     Psalm
    -0.06
     masked
    -0.06
    _SP
    -0.06
    POSITIVE LOGITS
     Eag
    0.07
    ênh
    0.06
     Milano
    0.06
    )은
    0.06
    Probably
    0.06
    Deployment
    0.06
    Robot
    0.06
     MessageBoxButton
    0.06
    Perform
    0.06
    darwin
    0.06
    Act Density 0.040%

    No Known Activations