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

    Neuronpedia

    INDEX
    Explanations

    throw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    secutive
    -0.08
    有利于
    -0.07
     Celsius
    -0.07
    .html
    -0.07
     headphone
    -0.07
     warranties
    -0.06
    Vis
    -0.06
    拓展
    -0.06
    箫
    -0.06
     Advocate
    -0.06
    POSITIVE LOGITS
     McCabe
    0.08
    scripción
    0.07
    rgyz
    0.07
    terdam
    0.07
     base
    0.07
    肩膀
    0.07
     improvised
    0.06
    国际合作
    0.06
     женщин
    0.06
    _student
    0.06
    Act Density 0.006%

    No Known Activations