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

    Neuronpedia

    INDEX
    Explanations

    clockwork

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Te
    0.42
    อบ
    0.38
    Nic
    0.38
    Deck
    0.38
    Bir
    0.38
    Little
    0.37
    Mic
    0.37
     Te
    0.36
    osur
    0.35
     Little
    0.35
    POSITIVE LOGITS
     кол
    0.43
     sinned
    0.40
    팟
    0.40
     snooze
    0.39
     bookArray
    0.38
     gil
    0.36
     Koll
    0.36
     coll
    0.35
     punk
    0.35
    opend
    0.35
    Act Density 0.002%

    No Known Activations