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

    Neuronpedia

    INDEX
    Explanations

    weekly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    я
    1.37
    <h6>
    1.20
    ení
    1.19
    ik
    1.18
     personnes
    1.17
     ata
    1.15
     cwd
    1.14
    ரத்தில்
    1.13
    haha
    1.09
    ب
    1.08
    POSITIVE LOGITS
    ो
    1.38
     edgecolor
    1.17
    consin
    1.12
     sanity
    1.07
    lık
    1.07
    ות
    1.05
    ના
    1.02
    bromo
    1.02
    ভুক্ত
    1.00
    lığını
    1.00
    Act Density 0.025%

    No Known Activations