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

    Neuronpedia

    INDEX
    Explanations

    concepts related to explanations and attributions in research contexts

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

    causal explanations or reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijanski
    -0.52
    WithIOException
    -0.47
     isNameExpr
    -0.45
    RetentionPolicy
    -0.45
    transQ
    -0.43
     snippetHide
    -0.41
    NameInMap
    -0.41
    сылкі
    -0.41
    isNameExpr
    -0.40
    uxxxx
    -0.39
    POSITIVE LOGITS
     Normdatei
    0.71
    GTCX
    0.68
    StoryboardSegue
    0.61
    RegistryLite
    0.53
    MemoryWarning
    0.51
    ConstraintMaker
    0.47
    WebVitals
    0.47
    WriteAttribute
    0.45
    SerializedSize
    0.45
     relâche
    0.44
    Act Density 0.181%

    No Known Activations