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

    Neuronpedia

    INDEX
    Explanations

    medical advice disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     publicKey
    0.30
    𒊩
    0.30
     logística
    0.28
     있지만
    0.28
     страница
    0.28
    ১২শ
    0.27
    ейчас
    0.27
    восто
    0.27
     cvec
    0.27
     процессо
    0.26
    POSITIVE LOGITS
     it
    0.35
    It
    0.35
    i
    0.35
     It
    0.32
    ,
    0.32
    Sub
    0.31
     (
    0.31
     will
    0.31
     quite
    0.31
     $\
    0.30
    Act Density 0.019%

    No Known Activations