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

    Neuronpedia

    INDEX
    Explanations

    multi-lingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    The
    0.34
    O
    0.29
    EY
    0.28
    and
    0.27
     verify
    0.27
    ו
    0.27
    Foot
    0.26
                 
    0.25
    E
    0.25
     फ़रवरी
    0.24
    POSITIVE LOGITS
    s
    0.44
     (
    0.31
    க்கு
    0.27
     you
    0.27
    ")
    0.26
    </h2>
    0.26
    ніх
    0.25
    坚定
    0.24
    你是
    0.24
     sociales
    0.23
    Act Density 0.375%

    No Known Activations