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

    Neuronpedia

    INDEX
    Explanations

    list formatting and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused1086>
    0.26
    <unused1112>
    0.26
     excer
    0.26
     problém
    0.26
     menopause
    0.25
    <unused274>
    0.25
    🕤
    0.25
    algebras
    0.24
    Pyrazole
    0.24
    <unused1826>
    0.24
    POSITIVE LOGITS
     "
    0.29
    //
    0.27
    0.27
    ՝
    0.27
     “
    0.26
    :
    0.25
    ：
    0.25
     T
    0.24
    可以选择
    0.24
     тип
    0.24
    Act Density 2.538%

    No Known Activations