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

    Neuronpedia

    INDEX
    Explanations

    grammatical elements and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bau
    0.39
    Тре
    0.39
    σταν
    0.38
    ned
    0.37
    ὐ
    0.37
     ron
    0.36
     बजर
    0.36
    预期
    0.36
    𝑽
    0.36
    KV
    0.35
    POSITIVE LOGITS
     tapping
    0.38
     <
    0.37
     trims
    0.37
    atypes
    0.37
     man
    0.36
     $|\
    0.36
     mel
    0.35
     agree
    0.35
     माना
    0.35
    ச்சர்
    0.35
    Act Density 0.000%

    No Known Activations