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

    Neuronpedia

    INDEX
    Explanations

    medical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    必须
    -0.07
    --------------------------------------------------------------------------↵
    -0.07
     ornaments
    -0.07
     """",↵
    -0.07
     Piano
    -0.07
    VV
    -0.06
    NFL
    -0.06
    jections
    -0.06
    Clip
    -0.06
    cordova
    -0.06
    POSITIVE LOGITS
     propagate
    0.06
     ruth
    0.06
     expérience
    0.06
    _alignment
    0.06
     мал
    0.06
     нали
    0.06
    그러
    0.06
     cruz
    0.06
    qing
    0.06
    _notifier
    0.06
    Act Density 0.163%

    No Known Activations