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

    Neuronpedia

    INDEX
    Explanations

    summarising or structured output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     വസ്തു
    0.43
    穸
    0.42
    及ひ
    0.42
     વ્યવ
    0.41
    嗳
    0.41
    鼐
    0.40
     பொதுவாக
    0.40
     заявления
    0.39
     کنترل
    0.39
     постро
    0.39
    POSITIVE LOGITS
    get
    0.54
    fi
    0.48
     tabletop
    0.47
     hadn
    0.45
    тные
    0.44
    тный
    0.44
     get
    0.44
    fs
    0.44
    driven
    0.42
    fes
    0.42
    Act Density 0.011%

    No Known Activations