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

    Neuronpedia

    INDEX
    Explanations

    numerical values and percentages related to statistical data

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

    zero or nothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſtand
    -0.52
     odkazy
    -0.50
     faſt
    -0.48
     houſe
    -0.47
     pleaſure
    -0.47
    makeText
    -0.46
     ſtre
    -0.46
     ſtill
    -0.45
    InputBorder
    -0.44
     leis
    -0.44
    POSITIVE LOGITS
     الحره
    0.60
     Zero
    0.50
    None
    0.49
    Zero
    0.48
     None
    0.48
     zero
    0.47
    nothing
    0.47
     NOTHING
    0.46
    zero
    0.46
    Nothing
    0.45
    Act Density 0.151%

    No Known Activations