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

    Neuronpedia

    INDEX
    Explanations

    common pronouns and introductory phrases in the text

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

    examples, introductions, or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.71
     gynhyrchwyd
    -0.60
    elemField
    -0.59
    bootstrapcdn
    -0.56
     Italijani
    -0.53
    SpringRunner
    -0.52
    ----</
    -0.50
    +="
    -0.50
    akaian
    -0.48
    IVEREF
    -0.48
    POSITIVE LOGITS
     popolari
    0.41
    댓
    0.35
    AsUp
    0.34
     possano
    0.33
     aurez
    0.31
     možná
    0.30
     Kinds
    0.30
     esistono
    0.30
     prácti
    0.29
     solltest
    0.29
    Act Density 0.001%

    No Known Activations