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

    Neuronpedia

    INDEX
    Explanations

    Simplicity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Underground
    -0.07
    phoneNumber
    -0.07
     Whit
    -0.07
    soever
    -0.06
     broadly
    -0.06
     Kaf
    -0.06
    worker
    -0.06
     pudding
    -0.06
    north
    -0.06
     Cast
    -0.06
    POSITIVE LOGITS
    ormsg
    0.07
     навк
    0.07
    iese
    0.06
     الطبي
    0.06
    logue
    0.06
     eauto
    0.06
    rgba
    0.06
     кри
    0.06
    _Debug
    0.06
    _finish
    0.06
    Act Density 0.012%

    No Known Activations