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

    Neuronpedia

    INDEX
    Explanations

    Rasa, developer, personal interests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تحميل
    0.68
    Falling
    0.64
    せる
    0.62
    जेंसी
    0.62
     पद्मा
    0.62
    بل
    0.61
    pam
    0.60
    ფ
    0.60
    avel
    0.59
    മല
    0.59
    POSITIVE LOGITS
     iter
    0.69
     chit
    0.69
     lign
    0.67
    얏
    0.66
     grated
    0.66
    ticks
    0.64
    🔊
    0.64
    MLLoader
    0.63
     Toch
    0.63
     cosmet
    0.62
    Act Density 0.013%

    No Known Activations