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

    Neuronpedia

    INDEX
    Explanations

    statements expressing certainty or emphasis about a subject

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

    why it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.46
    findpost
    -0.43
    AndEndTag
    -0.40
    Портал
    -0.40
     whether
    -0.39
     basically
    -0.38
     specify
    -0.38
     pregunto
    -0.37
     Basically
    -0.37
    basically
    -0.37
    POSITIVE LOGITS
    GOTREF
    0.59
    出版年
    0.49
    viewDidLoad
    0.49
     Италијани
    0.49
    rawDesc
    0.46
    之所以
    0.46
     dlaczego
    0.45
     australis
    0.44
     waarom
    0.44
    Климат
    0.44
    Act Density 0.018%

    No Known Activations