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

    Neuronpedia

    INDEX
    Explanations

    instances of criticism or comments regarding individuals or actions

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

    statements, remarks, or declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cities
    -0.29
     بلا
    -0.28
     dist
    -0.28
     families
    -0.28
     suits
    -0.27
     cur
    -0.26
    Inflater
    -0.26
    ặ
    -0.25
     packages
    -0.25
     Great
    -0.25
    POSITIVE LOGITS
     betweenstory
    0.78
     remarks
    0.71
     ujednoznacz
    0.70
     invokingState
    0.66
    writeField
    0.66
    StoryboardSegue
    0.65
     remark
    0.65
     Wiktionnaire
    0.65
     declaración
    0.64
    発言
    0.63
    Act Density 0.092%

    No Known Activations