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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating origins or sources of information

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

    where it comes from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     szóci
    -0.39
     NLI
    -0.34
     fără
    -0.34
     Receipt
    -0.34
    stylers
    -0.33
    )"),
    -0.32
     receipt
    -0.32
     Philadel
    -0.32
     jäm
    -0.32
    ἶ
    -0.32
    POSITIVE LOGITS
    uxxxx
    0.68
    setVerticalGroup
    0.63
    handleSubmit
    0.56
     Barnard
    0.56
    AsUp
    0.56
    CloseOperation
    0.51
    onAttach
    0.50
    transQ
    0.49
    featureID
    0.49
    httphttps
    0.49
    Act Density 0.012%

    No Known Activations