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

    Neuronpedia

    INDEX
    Explanations

    structured arguments and logical connections in text

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

    punctuation and spacing in text

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

    citations and technical phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -1.12
    ंदीखरीदारी
    -0.65
    richTextPanel
    -0.63
    CopyWith
    -0.62
    ($__
    -0.62
    :✨
    -0.61
     '\\;'
    -0.60
     GoogleFonts
    -0.60
    SerializedSize
    -0.59
    msgTypes
    -0.59
    POSITIVE LOGITS
     caccia
    0.55
     policiais
    0.53
    ็จ
    0.48
     nevoie
    0.47
     cleft
    0.47
     pungkas
    0.46
     resolving
    0.45
     Resolve
    0.45
     Acuerdo
    0.45
     mortos
    0.44
    Act Density 0.051%

    No Known Activations