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

    Neuronpedia

    INDEX
    Explanations

    serialVersionUID

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    beam
    -0.07
    余个
    -0.07
    oom
    -0.07
    ?,?,?,?,
    -0.07
    .."
    -0.07
    lox
    -0.07
    imports
    -0.07
    計
    -0.07
     competition
    -0.07
    .get
    -0.07
    POSITIVE LOGITS
    ereço
    0.08
    .widgets
    0.07
    (serial
    0.07
     kị
    0.07
     pkt
    0.07
    iculty
    0.07
    셰
    0.07
     inconvenient
    0.07
     synerg
    0.07
     arcane
    0.07
    Act Density 0.001%

    No Known Activations