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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns and values

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

    hyphen, dash, and period separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.59
     purpoſe
    -0.57
     myſelf
    -0.50
    таратура
    -0.49
     kasarigan
    -0.49
     ſte
    -0.47
    rungsseite
    -0.46
     pleaſure
    -0.45
     <<<<<<<<<<<<<<
    -0.43
     portable
    -0.41
    POSITIVE LOGITS
     DBNull
    0.49
    マイズ
    0.45
    ToBounds
    0.44
     numberOfRows
    0.43
    inSlope
    0.43
     الحره
    0.43
    $_['
    0.41
    ArrowToggle
    0.40
     RouterModule
    0.38
    writerow
    0.37
    Act Density 0.704%

    No Known Activations