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

    Neuronpedia

    INDEX
    Explanations

    programming and coding syntax elements

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

    Code, math, or technical language

    np_acts-logits-general · gemini-2.0-flash

    each words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gonic
    -0.44
    atigable
    -0.43
    terase
    -0.42
    codable
    -0.42
    lique
    -0.42
     queſta
    -0.42
    odiment
    -0.42
    principalTable
    -0.41
    mistry
    -0.41
     Dawes
    -0.41
    POSITIVE LOGITS
     each
    0.69
     nahilalakip
    0.57
    Each
    0.51
     Each
    0.50
     jeweils
    0.48
     EACH
    0.48
     Chwiliwch
    0.47
    each
    0.46
     jeweiligen
    0.46
     cherchés
    0.45
    Act Density 1.268%

    No Known Activations