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

    Neuronpedia

    INDEX
    Explanations

    pipeline run status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Pu
    0.45
    na
    0.42
    Kami
    0.42
    becomes
    0.42
    versus
    0.41
    i
    0.41
    inter
    0.40
    pu
    0.40
    ech
    0.40
    imu
    0.40
    POSITIVE LOGITS
     profinite
    0.40
     aten
    0.39
     முடியவில்லை
    0.39
    低温
    0.39
     attenuated
    0.39
     মিটার
    0.38
     میان
    0.38
     连接
    0.38
     ChIP
    0.38
     pommes
    0.38
    Act Density 0.000%

    No Known Activations