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

    Neuronpedia

    INDEX
    Explanations

    old

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aks
    -0.46
    rid
    -0.45
     vil
    -0.45
    keits
    -0.45
     fe
    -0.44
    ene
    -0.44
    ness
    -0.44
     }$
    -0.44
    eder
    -0.43
    xae
    -0.43
    POSITIVE LOGITS
     myſelf
    0.84
     Shakspeare
    0.83
     itſelf
    0.82
    IUrlHelper
    0.79
     Monfieur
    0.75
    <bos>
    0.73
    InstrumentedTest
    0.73
     himſelf
    0.73
     Roskov
    0.73
     للمعارف
    0.71
    Act Density 0.255%

    No Known Activations