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
     delle
    -0.06
     rugs
    -0.06
    ograf
    -0.06
    :'.$
    -0.06
    BLUE
    -0.06
    Languages
    -0.06
    -primary
    -0.06
    十三
    -0.06
    ι
    -0.06
    ｜
    -0.06
    POSITIVE LOGITS
    BB
    0.07
     účast
    0.06
     pek
    0.06
     manera
    0.06
     نوشته
    0.06
     complic
    0.06
     adorable
    0.06
    .<
    0.06
    preter
    0.06
     раздел
    0.06
    Act Density 0.018%

    No Known Activations