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

    Neuronpedia

    INDEX
    Explanations

    Python sets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JObject
    -0.07
     (@
    -0.07
     surfaced
    -0.07
     Pharmacy
    -0.06
    190
    -0.06
    _update
    -0.06
     Zoo
    -0.06
     Expected
    -0.06
     pharmacy
    -0.06
    !!↵↵
    -0.06
    POSITIVE LOGITS
    (Icons
    0.07
    ่อไป
    0.07
    [left
    0.06
     Dal
    0.06
    ipi
    0.06
     tık
    0.06
    -Key
    0.06
    必
    0.06
    мет
    0.06
     огранич
    0.06
    Act Density 0.022%

    No Known Activations