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

    Neuronpedia

    INDEX
    Explanations

    future possibilities or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    שוט
    0.54
    тың
    0.53
    FOR
    0.51
    мени
    0.50
    lamak
    0.49
    i
    0.47
    꺼
    0.46
    าย
    0.46
    etting
    0.46
    літ
    0.46
    POSITIVE LOGITS
     mutually
    0.43
     DR
    0.42
     revolution
    0.42
    ációs
    0.41
    在一
    0.40
    進
    0.40
     Gerät
    0.39
     ك
    0.39
     sync
    0.38
     drastically
    0.38
    Act Density 0.003%

    No Known Activations