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

    Neuronpedia

    INDEX
    Explanations

    Code/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Depending
    -0.06
     Mehr
    -0.06
     Radi
    -0.06
     Dia
    -0.06
     적
    -0.06
    stride
    -0.06
    HEMA
    -0.06
     Analog
    -0.06
     Gi�
    -0.06
    ській
    -0.06
    POSITIVE LOGITS
    游戏
    0.08
     produit
    0.07
    .Second
    0.07
     ark
    0.07
    .robot
    0.07
    ��
    0.07
     Tooltip
    0.06
    .follow
    0.06
     matrimon
    0.06
    _run
    0.06
    Act Density 0.000%

    No Known Activations