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

    Neuronpedia

    INDEX
    Explanations

    act ingredient algorithm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.52
     נו
    0.51
     attaché
    0.50
    多家
    0.47
    quisites
    0.47
    加入
    0.47
    附
    0.47
     जोड़ने
    0.46
     operativo
    0.46
     adhik
    0.46
    POSITIVE LOGITS
    Dirty
    0.46
    dental
    0.46
    gro
    0.44
     roar
    0.44
    ع
    0.43
    kiss
    0.43
    tos
    0.42
     सेंट
    0.42
    keyPressed
    0.42
    p
    0.42
    Act Density 0.000%

    No Known Activations