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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or conditionality in statements

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

    states reason or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     couvercle
    -0.35
     enfant
    -0.35
     dispositif
    -0.34
     montado
    -0.33
     GreatSchools
    -0.32
    会上
    -0.32
    RegistryLite
    -0.31
    -0.30
     Dritten
    -0.30
     prêtre
    -0.30
    POSITIVE LOGITS
    setVerticalGroup
    0.75
     disambiguazione
    0.67
    Diweddarwch
    0.63
     дописавши
    0.62
    SequentialGroup
    0.60
    AnchorStyles
    0.54
    RefNanny
    0.53
    MarshalTo
    0.51
    ArgsConstructor
    0.51
    fone
    0.51
    Act Density 0.047%

    No Known Activations