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

    Neuronpedia

    INDEX
    Explanations

    terms related to research methodology and study structure

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

    explaining study methodology and goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gynhyrchwyd
    -0.47
    TargetException
    -0.40
     setDate
    -0.39
    -0.39
     cl
    -0.38
    AutoScale
    -0.38
     setObject
    -0.37
    AutoField
    -0.36
     setType
    -0.36
     setPrice
    -0.36
    POSITIVE LOGITS
     henvisninger
    0.57
    providedIn
    0.50
     bluzka
    0.50
     sukienka
    0.47
    Personensuche
    0.46
    EndInit
    0.43
    körper
    0.42
     lenker
    0.42
     divisor
    0.41
     createState
    0.41
    Act Density 0.094%

    No Known Activations