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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rhs
    -0.07
     Nora
    -0.07
    apsible
    -0.06
    .TAG
    -0.06
     Кор
    -0.06
     영국
    -0.06
     warrant
    -0.06
    atak
    -0.06
    Volumes
    -0.06
     dipped
    -0.06
    POSITIVE LOGITS
     Prescription
    0.07
    _agg
    0.07
    comparison
    0.06
     мак
    0.06
     alone
    0.06
     significantly
    0.06
    =models
    0.06
     fading
    0.06
     philanth
    0.06
    поч
    0.06
    Act Density 0.034%

    No Known Activations