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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     economics
    -0.07
    \Abstract
    -0.07
    となっています
    -0.07
    扑
    -0.07
     Nevertheless
    -0.07
     то
    -0.06
     יותר
    -0.06
    icles
    -0.06
    ⼦
    -0.06
    纯净
    -0.06
    POSITIVE LOGITS
    ILLS
    0.07
    grep
    0.07
    股权转让
    0.07
    _concat
    0.07
    ꧈
    0.06
    几年前
    0.06
     Yugoslavia
    0.06
    口碑
    0.06
     squares
    0.06
    elseif
    0.06
    Act Density 0.003%

    No Known Activations