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

    Neuronpedia

    INDEX
    Explanations

    AI capabilities, human limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ju
    -0.07
    Mc
    -0.07
     Warm
    -0.06
    Warm
    -0.06
    하여
    -0.06
     integr
    -0.06
     Doğu
    -0.06
     judgments
    -0.06
     yans
    -0.06
    Lights
    -0.06
    POSITIVE LOGITS
     hết
    0.08
    NullPointerException
    0.06
     throwable
    0.06
    _fix
    0.06
     lắp
    0.06
    .URL
    0.06
     шк
    0.06
     حمل
    0.06
     retain
    0.06
    .Cast
    0.06
    Act Density 0.109%

    No Known Activations