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

    Neuronpedia

    INDEX
    Explanations

    online references and web links

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

    URLs and bracketed expressions

    np_acts-logits-general · gemini-2.0-flash

    URLs and markdown links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.53
    enumi
    -0.48
     rhestr
    -0.45
     pusi
    -0.45
     arşivlendi
    -0.44
    WithMany
    -0.43
    ALLOW
    -0.43
    الدراسه
    -0.43
    writeField
    -0.42
     πε
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.73
     propOrder
    0.70
    なぜか
    0.64
    localScale
    0.64
     Tapatalk
    0.63
    nope
    0.62
     ProtoMessage
    0.62
    adaptiveStyles
    0.61
     kasarigan
    0.58
    Nope
    0.58
    Act Density 0.022%

    No Known Activations