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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BTC
    -0.07
     Betting
    -0.07
     alors
    -0.07
     poorer
    -0.07
     brute
    -0.07
     pastors
    -0.07
     fois
    -0.07
     Alta
    -0.07
     Arbeit
    -0.07
     Guinea
    -0.07
    POSITIVE LOGITS
    骞
    0.07
    .numberOfLines
    0.07
    composed
    0.07
    综艺节目
    0.07
    .flowLayoutPanel
    0.07
    🍸
    0.07
    ascular
    0.06
    ㈪
    0.06
    ﮇ
    0.06
    cccc
    0.06
    Act Density 0.000%

    No Known Activations