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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical constructs and operations, particularly matrices and vectors

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

    Matrix/array rows and columns

    np_acts-logits-general · gemini-2.0-flash

    matrix rows and entries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FormTagHelper
    -0.55
    eabouts
    -0.52
    (:,:,
    -0.52
    ])]
    -0.51
    PageIndex
    -0.51
    meture
    -0.49
     ADM
    -0.49
    ahi
    -0.49
    InputBorder
    -0.48
     adv
    -0.47
    POSITIVE LOGITS
    writerow
    0.57
     gyhoeddwyd
    0.56
    row
    0.55
     row
    0.54
    AutoScaleMode
    0.53
     MainAxisSize
    0.52
     COLUMN
    0.52
    Hentet
    0.51
    Expedia
    0.51
    Row
    0.50
    Act Density 0.475%

    No Known Activations