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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to assumptions, predictions, and statistical analysis

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

    preceding a condition or reason

    np_acts-logits-general · gemini-2.0-flash

    reasoning and causal links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cyfeiriadau
    -0.44
    styleType
    -0.37
     naman
    -0.37
     Gegenwart
    -0.36
    сього
    -0.35
    spesies
    -0.35
    ADORES
    -0.35
    Cyfarwyddwr
    -0.35
    arrol
    -0.35
     Carr
    -0.34
    POSITIVE LOGITS
    OGND
    0.62
     متعلقه
    0.55
     resourceCulture
    0.53
    SharedDtor
    0.52
     offsets
    0.49
    astify
    0.47
    featureID
    0.47
    люс
    0.45
     counting
    0.45
    DockStyle
    0.45
    Act Density 0.726%

    No Known Activations