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

    Neuronpedia

    INDEX
    Explanations

    Legal licenses and citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     why
    -0.08
    key
    -0.08
     Edison
    -0.07
     leaving
    -0.07
     released
    -0.07
     artist
    -0.07
    提出
    -0.07
    ">\
    -0.07
    いい
    -0.07
    标题
    -0.07
    POSITIVE LOGITS
     Kiev
    0.07
    _ru
    0.07
    _draft
    0.07
    的教学
    0.07
    FromBody
    0.07
    姿
    0.07
    的应用
    0.06
     welcomes
    0.06
     commute
    0.06
    这两种
    0.06
    Act Density 0.010%

    No Known Activations