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

    Neuronpedia

    INDEX
    Explanations

    Section delimiters in papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    outputs
    -0.07
    ΑΔ
    -0.06
     punctuation
    -0.06
    ㅠㅠ
    -0.06
    nx
    -0.06
    -election
    -0.06
     Romero
    -0.06
     locate
    -0.05
    イド
    -0.05
    -changing
    -0.05
    POSITIVE LOGITS
    uling
    0.07
    _PLUGIN
    0.07
    .singleton
    0.06
     тяж
    0.06
     olduk
    0.06
    .define
    0.06
    国家
    0.06
    いつ
    0.06
     дина
    0.06
     реб
    0.06
    Act Density 0.005%

    No Known Activations