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

    Neuronpedia

    INDEX
    Explanations

    hash symbol or comment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ･･
    0.82
     ì
    0.68
     ـ
    0.66
    ꧂
    0.65
    ∙
    0.65
    ufieurs
    0.65
    ጢ
    0.64
    \_
    0.64
     createContext
    0.64
    ———
    0.63
    POSITIVE LOGITS
     #
    6.05
    #
    5.79
     (#
    4.14
    .#
    4.05
     \#
    3.96
    #,
    3.91
    ＃
    3.84
    ,#
    3.83
     $\#
    3.64
     #(
    3.63
    Act Density 0.849%

    No Known Activations