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

    Neuronpedia

    INDEX
    Explanations

    the word "how" in various contexts

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

    explaining how things work

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forState
    -0.45
     Scottish
    -0.38
     shouldn
    -0.37
    WaitGroup
    -0.35
     abbia
    -0.35
     dési
    -0.34
    arrête
    -0.34
     must
    -0.34
     mustn
    -0.34
     pouvant
    -0.33
    POSITIVE LOGITS
    المناصب
    0.64
    +#+#
    0.62
     GenerationType
    0.62
     näin
    0.55
     how
    0.52
     way
    0.51
     ahogy
    0.51
     inilah
    0.49
     worauf
    0.49
     pinulongan
    0.47
    Act Density 0.002%

    No Known Activations