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

    Neuronpedia

    INDEX
    Explanations

    Site

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Public
    -0.07
    _income
    -0.06
     Generating
    -0.06
    erta
    -0.06
    setType
    -0.06
    VERSION
    -0.06
     Topics
    -0.06
     BELOW
    -0.06
    Wrong
    -0.06
     because
    -0.06
    POSITIVE LOGITS
     Sach
    0.06
     UNESCO
    0.06
    場
    0.06
    基金
    0.06
    _Re
    0.06
     Rep
    0.06
     centro
    0.06
     venues
    0.06
     реє
    0.06
    .fre
    0.06
    Act Density 0.007%

    No Known Activations