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

    Neuronpedia

    INDEX
    Explanations

    explaining a question or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     সেগুলো
    0.36
    The
    0.33
    Good
    0.32
    ↵
    0.32
    fl
    0.31
    those
    0.30
     esetén
    0.30
     The
    0.29
    тре
    0.29
    R
    0.29
    POSITIVE LOGITS
     itself
    0.63
    本身
    0.61
    本身的
    0.53
     مذکور
    0.40
     자체가
    0.39
     자체
    0.38
    自体
    0.37
    টির
    0.37
    টি
    0.35
     holder
    0.35
    Act Density 0.070%

    No Known Activations