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

    Neuronpedia

    INDEX
    Explanations

    perceived threats or danger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sufrimiento
    0.40
    航
    0.40
     एक्सपेक्ट
    0.39
    ábban
    0.38
     airspace
    0.38
    unoassay
    0.36
    旋
    0.36
    粗
    0.36
    зь
    0.35
     Lollipop
    0.35
    POSITIVE LOGITS
    랩
    0.41
    udiant
    0.40
    Cast
    0.40
    acci
    0.38
    oni
    0.38
     Trotsky
    0.37
    Graduate
    0.37
     Cardi
    0.37
    Dental
    0.36
    Bund
    0.35
    Act Density 0.000%

    No Known Activations