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

    Neuronpedia

    INDEX
    Explanations

    w http

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ത്യാ
    0.45
    நெ
    0.41
     silica
    0.38
    bak
    0.37
    สำเร็จ
    0.36
    Mediterranean
    0.36
     Bamberg
    0.36
     bak
    0.35
    Lux
    0.35
     calci
    0.35
    POSITIVE LOGITS
    *:
    0.41
     Substituting
    0.40
     Voraus
    0.38
    _:
    0.38
    が必要です
    0.37
    拣
    0.37
    膺
    0.37
     പൊലീസ്
    0.37
    равни
    0.37
    ："
    0.36
    Act Density 0.000%

    No Known Activations