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

    Neuronpedia

    INDEX
    Explanations

    light

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     canoe
    -0.07
    ū
    -0.07
    /Linux
    -0.07
     suic
    -0.07
     eh
    -0.07
     어떤
    -0.06
     quantify
    -0.06
     Finnish
    -0.06
     sincer
    -0.06
    .SplitContainer
    -0.06
    POSITIVE LOGITS
    cream
    0.07
    ירוע
    0.07
    準
    0.07
     getPage
    0.06
    '(
    0.06
    (dummy
    0.06
    umping
    0.06
    (disposing
    0.06
    _PED
    0.06
    停留
    0.06
    Act Density 0.060%

    No Known Activations