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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tale
    -0.07
     Prairie
    -0.07
    ichage
    -0.06
    evaluation
    -0.06
    rstrip
    -0.06
    -tier
    -0.06
    ())
    -0.06
    دواج
    -0.06
    诺
    -0.06
    ्त
    -0.06
    POSITIVE LOGITS
    worksheet
    0.07
    wig
    0.07
     belum
    0.07
    .tm
    0.07
    чие
    0.07
     Contractors
    0.06
     poses
    0.06
    ]+\
    0.06
     YELLOW
    0.06
     @_
    0.06
    Act Density 0.004%

    No Known Activations