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

    Neuronpedia

    INDEX
    Explanations

    numerical values and related data points

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

    man topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كومونز
    -0.61
    AddTagHelper
    -0.56
    ORNING
    -0.55
    IBOutlet
    -0.50
    TAINMENT
    -0.49
     InputDecoration
    -0.48
    nastics
    -0.47
     springfox
    -0.47
     للاسماء
    -0.47
    期刊论文
    -0.47
    POSITIVE LOGITS
    adple
    0.39
    fromCharCode
    0.37
    dangerous
    0.37
     BoxFit
    0.35
    Parcelize
    0.35
    blico
    0.35
     dangerous
    0.35
     helpline
    0.35
     nakalista
    0.35
     upon
    0.33
    Act Density 0.002%

    No Known Activations