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

    Neuronpedia

    INDEX
    Explanations

    hidden illicit items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SER
    -0.06
     司
    -0.06
     MPU
    -0.06
     зас
    -0.06
    enské
    -0.06
    (fontSize
    -0.06
     �
    -0.06
    Op
    -0.06
    ουλ
    -0.06
     MERCHANTABILITY
    -0.06
    POSITIVE LOGITS
    	Create
    0.08
     Reagan
    0.08
    collapse
    0.07
    .gamma
    0.07
    ichick
    0.06
    .Lookup
    0.06
     Diagnosis
    0.06
     ages
    0.06
     ง
    0.06
     contract
    0.06
    Act Density 0.003%

    No Known Activations