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

    Neuronpedia

    INDEX
    Explanations

    phrases related to coding logic and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    evaluating alternatives or offers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CppMethod
    -0.42
     signUp
    -0.33
     dési
    -0.33
    verständlich
    -0.31
    ERÍA
    -0.31
     jaringan
    -0.30
    前进
    -0.30
     revanche
    -0.30
    户
    -0.29
    BeginInit
    -0.29
    POSITIVE LOGITS
    NameInMap
    0.78
    +#+#
    0.73
    Tikang
    0.73
    TagMode
    0.69
     للمعارف
    0.68
    angliski
    0.68
    nezeu
    0.68
     estekak
    0.68
    RectangleBorder
    0.68
     ivelany
    0.66
    Act Density 0.007%

    No Known Activations