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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing curiosity or surprise regarding situations

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

    explaining why or giving reasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.70
     gyhoeddwyd
    -0.49
     Wiktionnaire
    -0.47
    ècie
    -0.47
    İstinadlar
    -0.47
    دانشنامهٔ
    -0.46
    Sucesor
    -0.44
     testSet
    -0.44
    -0.44
    PostMapping
    -0.42
    POSITIVE LOGITS
     reason
    0.51
    难怪
    0.50
     why
    0.48
     ragione
    0.46
     razão
    0.46
     razón
    0.45
    latego
    0.44
     therefore
    0.44
    sprechend
    0.43
     reasons
    0.43
    Act Density 0.124%

    No Known Activations