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

    Neuronpedia

    INDEX
    Explanations

    granting permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bombardment
    0.49
     Mahabhar
    0.45
     prosecutions
    0.44
     arid
    0.43
     bouncy
    0.43
    や
    0.42
    Transformer
    0.42
     bruising
    0.42
     ruins
    0.41
     developments
    0.41
    POSITIVE LOGITS
     pardon
    0.50
     партии
    0.42
    şiktaş
    0.42
     согласи
    0.42
    谒
    0.42
    ía
    0.42
     permission
    0.42
    芗
    0.41
     уве
    0.41
     принима
    0.41
    Act Density 0.001%

    No Known Activations