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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doctr
    -0.07
     เก
    -0.06
     Macy
    -0.06
     zpráv
    -0.06
     mojo
    -0.06
     senators
    -0.06
     knowingly
    -0.06
     Mã
    -0.06
     많
    -0.06
    monto
    -0.06
    POSITIVE LOGITS
    Right
    0.08
     Ref
    0.08
    /Auth
    0.07
    reds
    0.07
    ΟΥ
    0.07
    ref
    0.07
    _corner
    0.07
    发
    0.07
    190
    0.07
    рей
    0.06
    Act Density 0.004%

    No Known Activations