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

    Neuronpedia

    INDEX
    Explanations

    legal/business context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commanded
    -0.06
     بپ
    -0.06
    _tgt
    -0.06
     lab
    -0.06
    赢
    -0.06
    <any
    -0.06
     treaties
    -0.06
     至
    -0.06
    .cur
    -0.06
     manip
    -0.06
    POSITIVE LOGITS
    Xã
    0.07
    ianne
    0.07
    =email
    0.07
     ieee
    0.06
    -mounted
    0.06
     fortunately
    0.06
    [--
    0.06
    わけ
    0.06
     너무
    0.06
     protester
    0.06
    Act Density 0.059%

    No Known Activations