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

    Neuronpedia

    INDEX
    Explanations

    doctor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SEQUENCE
    -0.07
     Massage
    -0.07
    مرحلة
    -0.07
    loe
    -0.07
    _magic
    -0.07
    次数
    -0.07
    Parms
    -0.06
    حلة
    -0.06
    밖에
    -0.06
    predicate
    -0.06
    POSITIVE LOGITS
     posit
    0.09
     Blob
    0.07
    -
↵
    0.07
     (-
    0.07
    �
    0.07
     المؤ
    0.06
    😆
    0.06
     pri
    0.06
    frog
    0.06
     voi
    0.06
    Act Density 0.004%

    No Known Activations