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

    Neuronpedia

    INDEX
    Explanations

    specific numerical or structural data in a technical context

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

    numbers and punctuation in mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.45
     parti
    -0.42
     IM
    -0.42
     הרי
    -0.41
     πρό
    -0.41
    edes
    -0.40
     Cast
    -0.40
     unpaid
    -0.40
    onOptions
    -0.39
    pieler
    -0.38
    POSITIVE LOGITS
    новништво
    0.59
    copg
    0.58
    VYMaps
    0.52
     виправивши
    0.51
    IntoConstraints
    0.49
     betweenstory
    0.49
    featureID
    0.47
     myſelf
    0.46
    AsUp
    0.45
    URLException
    0.45
    Act Density 0.141%

    No Known Activations