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

    Neuronpedia

    INDEX
    Explanations

    .com URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     exquis
    0.08
    פות
    0.08
     pura
    0.07
     імені
    0.07
    <bos>
    0.07
    Helvetica
    0.07
     pique
    0.07
    }'
    0.07
     bodhis
    0.07
    tolyl
    0.07
    POSITIVE LOGITS
    স
    0.10
    𝘭
    0.09
    𝘴
    0.08
    க்கொண்டு
    0.08
    نت
    0.08
    𝘁
    0.08
    有
    0.08
    ర్
    0.08
    ត់
    0.08
    ई
    0.07
    Act Density 0.007%

    No Known Activations