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

    Neuronpedia

    INDEX
    Explanations

    statements or reports that involve the act of speaking or writing

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

    reporting verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.30
    tidak
    -0.26
     x
    -0.25
     non
    -0.24
     uncertainty
    -0.24
     stage
    -0.24
    s
    -0.23
     T
    -0.23
     able
    -0.23
    '
    -0.23
    POSITIVE LOGITS
     Administrativna
    1.00
     فريبيس
    0.85
    GEBURTSDATUM
    0.83
    iſchen
    0.81
     imagui
    0.81
    <unused74>
    0.80
     ſeine
    0.80
    <unused52>
    0.80
    <unused8>
    0.80
    <unused3>
    0.80
    Act Density 0.046%

    No Known Activations