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

    Neuronpedia

    INDEX
    Explanations

    a way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ëve
    0.40
     çıkt
    0.40
    ႂ
    0.40
     synthesize
    0.39
    *{\
    0.38
     terme
    0.38
     атрибу
    0.38
     ("/
    0.38
    ("{}
    0.38
    なわち
    0.38
    POSITIVE LOGITS
     curiously
    0.50
    toys
    0.46
    Toy
    0.46
     Toys
    0.45
     toys
    0.45
    Jimmy
    0.43
     Jimmy
    0.43
     Toy
    0.42
    Toys
    0.42
     gioc
    0.41
    Act Density 0.000%

    No Known Activations