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

    Neuronpedia

    INDEX
    Explanations

    Image editing software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (horizontal
    -0.08
    .GetName
    -0.07
     Skinner
    -0.06
     tighter
    -0.06
    /device
    -0.06
    屍
    -0.06
     actually
    -0.06
     japanese
    -0.06
     биз
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    常用
    0.08
    //[
    0.07
    arrow
    0.07
    可用
    0.07
    _altern
    0.07
    经开区
    0.07
    AAA
    0.07
     Memory
    0.07
    layers
    0.07
    Joy
    0.06
    Act Density 0.075%

    No Known Activations