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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foregoing
    -0.08
     gallons
    -0.07
     colonies
    -0.07
    _activity
    -0.07
     colony
    -0.07
     نوش
    -0.07
    This
    -0.07
     patriotic
    -0.07
    .invoke
    -0.06
     Holocaust
    -0.06
    POSITIVE LOGITS
    _env
    0.06
    άντα
    0.06
    ----------↵↵
    0.06
    Turkey
    0.06
     leh
    0.06
    yclerview
    0.06
     [.
    0.06
    ekkür
    0.06
    .yml
    0.06
     Auburn
    0.05
    Act Density 0.007%

    No Known Activations