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

    Neuronpedia

    INDEX
    Explanations

    MG

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "")↵
    -0.07
     Begins
    -0.07
    .break
    -0.07
    _via
    -0.06
    冲
    -0.06
     relay
    -0.06
     Р
    -0.06
     sıcak
    -0.06
     fueled
    -0.06
    yaml
    -0.06
    POSITIVE LOGITS
    グラ
    0.06
    DCALL
    0.06
    .visitVarInsn
    0.06
     Punk
    0.06
     Variable
    0.06
     ژوئ
    0.06
     Doğ
    0.06
    授
    0.06
     anomalies
    0.06
    นต
    0.06
    Act Density 0.357%

    No Known Activations