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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (expression
    -0.06
     ST
    -0.06
     함께
    -0.06
    167
    -0.06
    sd
    -0.06
    .eye
    -0.06
     lạ
    -0.06
     gần
    -0.06
    uncios
    -0.06
    迎
    -0.06
    POSITIVE LOGITS
     Şampiyon
    0.07
     true
    0.07
    noc
    0.06
     yap
    0.06
    ند
    0.06
    ्दर
    0.06
    &(
    0.06
    oring
    0.06
     blanc
    0.06
     animal
    0.06
    Act Density 0.000%

    No Known Activations