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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()(
    -0.08
    .xlabel
    -0.07
     ein
    -0.07
     surgeons
    -0.07
     lawmaker
    -0.07
    _tcb
    -0.07
    Terminate
    -0.07
    lab
    -0.06
     Physician
    -0.06
     preacher
    -0.06
    POSITIVE LOGITS
    的认可
    0.07
    モ
    0.07
    �
    0.07
    植被
    0.07
    =batch
    0.07
     côt
    0.07
    께서
    0.07
    �
    0.06
    .Unique
    0.06
    ourney
    0.06
    Act Density 0.047%

    No Known Activations