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

    Neuronpedia

    INDEX
    Explanations

    box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -alert
    -0.07
    POCH
    -0.07
    ерти
    -0.06
     ア
    -0.06
    _WIDTH
    -0.06
    _observer
    -0.06
    (y
    -0.06
    .inverse
    -0.06
     Track
    -0.06
    (t
    -0.06
    POSITIVE LOGITS
     espos
    0.07
    Het
    0.06
     سفید
    0.06
     организа
    0.06
    DidAppear
    0.06
     Latvia
    0.06
     Locke
    0.06
    desk
    0.06
     propos
    0.06
     cozy
    0.06
    Act Density 0.004%

    No Known Activations