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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software components and modifications

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

    Texts that mention making changes or modifications

    np_acts-logits-general · gemini-2.0-flash

    adding, changing, modifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Convergence
    -0.48
    SerializedName
    -0.48
    StrictMode
    -0.46
     AutoMapper
    -0.43
    zeczy
    -0.43
    unakan
    -0.43
    愧
    -0.42
     combed
    -0.42
    結果は
    -0.42
     Alcalde
    -0.41
    POSITIVE LOGITS
     change
    1.11
    Changing
    1.10
     Changing
    1.07
     changing
    1.06
    change
    1.05
     Change
    1.05
     changes
    1.04
     Changes
    1.02
    changing
    0.99
    Change
    0.99
    Act Density 0.575%

    No Known Activations