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

    Neuronpedia

    INDEX
    Explanations

    mathematical matrices and their representations in various contexts

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

    matrix construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enterOuterAlt
    -0.66
    tagHelperRunner
    -0.66
    
    -0.54
    MethodManager
    -0.52
    脚注の使い方
    -0.51
    outSlope
    -0.49
    OrNil
    -0.46
    FTFY
    -0.46
    atguigu
    -0.45
    \{\\
    -0.44
    POSITIVE LOGITS
     matrix
    1.09
     Matrix
    0.97
    Matrix
    0.93
    matrix
    0.93
     matrices
    0.87
     matrice
    0.82
     MATRIX
    0.82
     matriz
    0.78
     Matrices
    0.78
    矩阵
    0.77
    Act Density 0.049%

    No Known Activations