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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .begin
    -0.08
    mj
    -0.07
     avoiding
    -0.07
    prep
    -0.07
    移交
    -0.07
    exampleInput
    -0.07
     journals
    -0.07
    妒
    -0.07
    تصف
    -0.07
    nowled
    -0.07
    POSITIVE LOGITS
    itt
    0.08
    יסט
    0.07
    광
    0.07
    얕
    0.07
    ulture
    0.07
    0.06
     Anglic
    0.06
    yang
    0.06
     getChild
    0.06
    واق
    0.06
    Act Density 0.080%

    No Known Activations