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

    Neuronpedia

    INDEX
    Explanations

    Future events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medicine
    -0.07
    -car
    -0.07
     HBO
    -0.06
    \Exception
    -0.06
    _list
    -0.06
     engines
    -0.06
     cent
    -0.06
     MDB
    -0.06
     sem
    -0.06
    softmax
    -0.06
    POSITIVE LOGITS
    "),"
    0.07
    rell
    0.07
     alien
    0.07
     ():
    0.06
     Proj
    0.06
    жди
    0.06
     şark
    0.06
    _SDK
    0.06
    UAL
    0.06
     ندار
    0.06
    Act Density 0.143%

    No Known Activations