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

    Neuronpedia

    INDEX
    Explanations

    placeholders and wildcards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鹃
    0.77
     instruct
    0.71
     Illustrator
    0.71
    lwjgl
    0.70
     advocating
    0.70
     instructions
    0.69
     ribs
    0.69
    Iv
    0.69
     advocates
    0.69
     anvil
    0.67
    POSITIVE LOGITS
     (?
    2.35
    ,?
    2.17
     ??
    2.10
     ?
    2.01
     ?.
    1.95
     ????
    1.87
    (?
    1.87
    .??
    1.83
     (?)
    1.78
    =?
    1.75
    Act Density 0.034%

    No Known Activations