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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers or indices

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

    Code or markup syntax

    np_acts-logits-general · gemini-2.0-flash

    cause and effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ところです
    -0.54
     vers
    -0.51
    GraphicsUnit
    -0.51
    grà
    -0.51
     }}"></
    -0.51
     aper
    -0.49
    DidChange
    -0.48
     Mora
    -0.48
    %@",
    -0.47
    vula
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.86
    :+:
    0.73
     propOrder
    0.63
    허
    0.61
    CAUSE
    0.59
     préfé
    0.58
     الحره
    0.57
     يتيمه
    0.56
    cause
    0.56
    #+#
    0.56
    Act Density 0.063%

    No Known Activations