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

    Neuronpedia

    INDEX
    Explanations

    AI's Programming/Purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     их
    0.37
     complicate
    0.36
    이야
    0.36
    Form
    0.34
    看起来
    0.34
     نخست
    0.34
    em
    0.33
    他们的
    0.33
    ík
    0.33
    이라고
    0.33
    POSITIVE LOGITS
     cannot
    0.45
    旨在
    0.45
     renforc
    0.40
     unable
    0.40
     powerless
    0.40
     bertujuan
    0.40
     couldn
    0.39
     checked
    0.39
     strives
    0.38
     actively
    0.38
    Act Density 0.229%

    No Known Activations