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

    Neuronpedia

    INDEX
    Explanations

    fear control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    疱
    0.41
    Dig
    0.41
    焊
    0.41
     সাপ্তাহিক
    0.40
     salido
    0.40
    Seit
    0.40
     نثر
    0.40
    chy
    0.39
    魘
    0.39
    দেন
    0.39
    POSITIVE LOGITS
     spills
    0.41
    ...";
    0.39
     respond
    0.39
    ,”
    0.38
    ackerel
    0.38
     ಔ
    0.38
    ="("
    0.37
     கலங்கரை
    0.37
    ilities
    0.36
     proxim
    0.36
    Act Density 0.001%

    No Known Activations