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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abcd
    -0.07
    正是
    -0.07
    甡
    -0.07
     tasked
    -0.07
    CAF
    -0.06
    �
    -0.06
    烔
    -0.06
    应聘
    -0.06
     nouns
    -0.06
    崃
    -0.06
    POSITIVE LOGITS
    كل
    0.08
    _Application
    0.08
    SAN
    0.08
    APPLE
    0.07
    ختار
    0.07
    прос
    0.07
    Culture
    0.07
    罰
    0.07
    Qualifier
    0.07
     Serie
    0.07
    Act Density 0.019%

    No Known Activations