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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    operative
    0.40
    ématique
    0.40
    erre
    0.38
     Archers
    0.38
    ⚭
    0.38
    cinoma
    0.38
     Mare
    0.37
    second
    0.37
     NVIC
    0.37
     disband
    0.37
    POSITIVE LOGITS
     myself
    0.43
     kontrakt
    0.41
    contract
    0.39
     contract
    0.39
    समाज
    0.36
     Portman
    0.36
    TaskPojo
    0.36
    凝
    0.36
     коюмдар
    0.36
     ladr
    0.36
    Act Density 0.001%

    No Known Activations