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

    Neuronpedia

    INDEX
    Explanations

    Okonomiyaki and Takoyaki

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pokud
    0.46
    ターゲット
    0.46
    যদি
    0.46
    耇
    0.44
     nhá
    0.43
    㖵
    0.43
    Kisi
    0.43
    Если
    0.42
    lemish
    0.42
     حقیقی
    0.42
    POSITIVE LOGITS
     creates
    0.46
    fmt
    0.44
     added
    0.40
     juggling
    0.40
     juggle
    0.40
     creation
    0.39
     allocates
    0.39
     flexibility
    0.38
    most
    0.38
     apl
    0.38
    Act Density 0.005%

    No Known Activations