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

    Neuronpedia

    INDEX
    Explanations

    multi-language phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ρέ
    0.48
    C
    0.46
     moveable
    0.44
    ssl
    0.44
    repetitions
    0.43
    tj
    0.42
    后的
    0.42
     Imagin
    0.42
    菌
    0.42
    repeat
    0.41
    POSITIVE LOGITS
    Week
    0.51
     бух
    0.50
    Bucket
    0.49
     energ
    0.49
    ╹
    0.48
     уда
    0.48
    kimi
    0.48
     unu
    0.48
     असतो
    0.47
     เอง
    0.47
    Act Density 0.000%

    No Known Activations