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

    Neuronpedia

    INDEX
    Explanations

    beneficial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STOP
    -0.07
    _ra
    -0.07
    :"
    -0.07
    signup
    -0.07
     ICU
    -0.06
    ERRU
    -0.06
     numéro
    -0.06
    KO
    -0.06
     ört
    -0.06
     spanking
    -0.06
    POSITIVE LOGITS
     beneficial
    0.09
     hemat
    0.07
    mercial
    0.07
    Blood
    0.07
    Benef
    0.07
    benef
    0.07
     عملية
    0.07
    Benefits
    0.07
     benefits
    0.07
     분
    0.06
    Act Density 0.004%

    No Known Activations