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

    Neuronpedia

    INDEX
    Explanations

    generating specific text content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Req
    0.46
    خر
    0.44
    leqq
    0.42
    Lance
    0.41
    蝠
    0.40
    梟
    0.40
    ണ്
    0.39
    κών
    0.39
     তি
    0.38
    leq
    0.38
    POSITIVE LOGITS
     Wyn
    0.40
     सरल
    0.39
    apons
    0.38
    ingen
    0.38
    yn
    0.38
     Amend
    0.38
    វិញ
    0.38
    yim
    0.38
    kje
    0.38
     birbirinden
    0.38
    Act Density 0.000%

    No Known Activations