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

    Neuronpedia

    INDEX
    Explanations

    prohibits or restricts actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     elucidation
    0.36
     ritor
    0.36
     tych
    0.32
     zejména
    0.30
     vem
    0.30
     momentous
    0.29
     των
    0.29
     suave
    0.29
     scoperta
    0.29
     fruitful
    0.29
    POSITIVE LOGITS
     violate
    0.32
     illegally
    0.31
     нару
    0.31
     unfairly
    0.30
    包含
    0.30
    beitet
    0.30
     violates
    0.29
     prohibits
    0.29
     напрямую
    0.29
    限制
    0.29
    Act Density 0.000%

    No Known Activations