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

    Neuronpedia

    INDEX
    Explanations

    code element followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒂗
    0.46
    SearchCV
    0.41
    ರೆ
    0.40
    ">-
    0.39
    ৃঙ্খলা
    0.39
    wali
    0.38
    メタル
    0.38
    >(</
    0.38
    amo
    0.37
    భర
    0.36
    POSITIVE LOGITS
    :
    2.03
     :
    1.98
    ：
    1.70
    ::
    1.69
    :$
    1.59
    :"
    1.54
    :_
    1.52
    .:
    1.51
    :'
    1.50
    :&
    1.50
    Act Density 0.174%

    No Known Activations