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

    Neuronpedia

    INDEX
    Explanations

    Cognitive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    د
    1.36
    dom
    1.26
    นั่ง
    1.11
    dan
    1.11
    ds
    1.06
    rangian
    1.00
    denoted
    0.98
     sorely
    0.98
    tség
    0.97
    有点
    0.97
    POSITIVE LOGITS
    ITION
    1.23
    ieszka
    1.17
    भ
    1.11
    الد
    1.10
    ționale
    1.10
    isance
    1.05
    ITIVE
    1.04
    ωσ
    1.01
    𝙤
    1.00
    雰囲気
    1.00
    Act Density 0.039%

    No Known Activations