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

    Neuronpedia

    INDEX
    Explanations

    springframework code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ভেদ
    0.97
    пис
    0.92
    чі
    0.83
     devote
    0.83
    чого
    0.82
    тка
    0.81
    ïdes
    0.78
    cted
    0.77
    пись
    0.77
     possibly
    0.77
    POSITIVE LOGITS
    springframework
    1.34
    鯛
    0.82
     비해
    0.77
     kamp
    0.76
     suprem
    0.74
     ਆਪਣ
    0.74
    squirrel
    0.73
    apache
    0.72
     Aesthetic
    0.71
    𝗸
    0.70
    Act Density 0.001%

    No Known Activations