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

    Neuronpedia

    INDEX
    Explanations

    graph theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    атика
    -0.08
    _BOX
    -0.08
    编号
    -0.08
    _ENDIAN
    -0.08
    盒
    -0.08
     serde
    -0.08
     BOX
    -0.08
    轴
    -0.07
    顺
    -0.07
    Label
    -0.07
    POSITIVE LOGITS
    েউ
    0.10
    average
    0.09
     प्रतिशत
    0.09
    ufficient
    0.09
    indest
    0.09
    density
    0.09
     average
    0.09
     generous
    0.09
     guarantees
    0.09
     generosity
    0.09
    Act Density 0.021%

    No Known Activations