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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cure
    -0.07
     myself
    -0.07
    _transient
    -0.06
    _repo
    -0.06
    know
    -0.06
     innov
    -0.06
     quests
    -0.06
    _station
    -0.06
     gods
    -0.06
     prevent
    -0.06
    POSITIVE LOGITS
     racism
    0.07
     IMS
    0.06
    ARTH
    0.06
     Autodesk
    0.06
    Numero
    0.06
    _deck
    0.06
     roadway
    0.06
     driveway
    0.06
    Posted
    0.06
    /yyyy
    0.06
    Act Density 0.008%

    No Known Activations