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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     requesting
    -0.08
    opping
    -0.06
     incap
    -0.06
    erged
    -0.06
     words
    -0.06
     NFL
    -0.06
    yx
    -0.06
    地址
    -0.06
    文
    -0.06
     OTHERWISE
    -0.06
    POSITIVE LOGITS
     yaşayan
    0.07
    (common
    0.07
     Sah
    0.07
    iao
    0.06
    much
    0.06
     İh
    0.06
    jni
    0.06
     розрах
    0.06
    щё
    0.06
     креп
    0.06
    Act Density 0.003%

    No Known Activations