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

    Neuronpedia

    INDEX
    Explanations

    glass and wood containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     என்று
    0.27
     результате
    0.27
     wyniku
    0.27
     क्योंकि
    0.26
     резулта
    0.26
     результат
    0.25
     чего
    0.25
     શું
    0.25
     regulation
    0.24
     ஆகியவை
    0.24
    POSITIVE LOGITS
    en
    0.43
    ar
    0.40
    et
    0.36
    os
    0.35
    ent
    0.33
    ik
    0.33
    em
    0.33
    ia
    0.32
    ers
    0.31
    ed
    0.29
    Act Density 0.000%

    No Known Activations