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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationship or association involving "with."

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

    describing qualities or contents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.50
     disambiguazione
    -0.46
     fabricants
    -0.41
    ̈́
    -0.40
    Notae
    -0.40
     War
    -0.37
    }`}
    -0.36
    Numerade
    -0.36
     jeans
    -0.36
     rheumatism
    -0.36
    POSITIVE LOGITS
     extensive
    0.50
     Extensive
    0.47
    Extensive
    0.46
     kombinasi
    0.45
    extensive
    0.44
    ocas
    0.43
     przes
    0.43
     terbuka
    0.43
     outstanding
    0.43
    chaub
    0.42
    Act Density 0.059%

    No Known Activations