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

    Neuronpedia

    INDEX
    Explanations

    references to the implementation of features in programming contexts

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

    something implemented

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.57
    saraba
    -0.48
     auroit
    -0.47
     héri
    -0.46
    ValueStyle
    -0.45
    armor
    -0.44
    xase
    -0.44
    startY
    -0.43
    agli
    -0.42
    DRAG
    -0.42
    POSITIVE LOGITS
     implemented
    1.41
    implemented
    1.35
     Implemented
    1.14
    Implemented
    1.13
     implement
    0.95
     implements
    0.80
     Implement
    0.79
     IMPLEMENT
    0.78
     implementing
    0.76
    implement
    0.69
    Act Density 0.024%

    No Known Activations