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

    Neuronpedia

    INDEX
    Explanations

    asciminib

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੀ
    1.85
     anak
    1.75
    lerde
    1.69
     Donec
    1.66
    al
    1.64
     headache
    1.59
    𝗿
    1.59
    tumor
    1.56
    쪽에
    1.56
     donc
    1.53
    POSITIVE LOGITS
    </tr>
    1.60
    ist
    1.58
    с
    1.55
    ق
    1.48
    utives
    1.46
    Respondent
    1.40
    jší
    1.40
    যেন
    1.39
    šće
    1.34
    it
    1.33
    Act Density 0.001%

    No Known Activations