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

    Neuronpedia

    INDEX
    Explanations

    references to vectors and their relationships

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

    vectors and matrices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Howell
    -0.37
    getOriginal
    -0.36
    Explicación
    -0.35
     inspiração
    -0.34
    ="./
    -0.34
     specialties
    -0.34
     specialty
    -0.34
     Higgins
    -0.33
     graça
    -0.33
    пит
    -0.32
    POSITIVE LOGITS
     matrices
    0.88
     Matrices
    0.87
     matrix
    0.82
    matrices
    0.73
    矩阵
    0.71
     tensors
    0.71
     matrice
    0.71
    Matrices
    0.69
     vectors
    0.66
     tensor
    0.65
    Act Density 0.071%

    No Known Activations