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

    Neuronpedia

    INDEX
    Explanations

    train test split data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Https
    -0.07
    Tem
    -0.07
     Na
    -0.07
    NGTH
    -0.07
    	o
    -0.07
     contest
    -0.07
     Jwt
    -0.07
     competit
    -0.06
    ortal
    -0.06
     Sche
    -0.06
    POSITIVE LOGITS
    .IOException
    0.06
    _InitStructure
    0.06
    .BUTTON
    0.06
    verter
    0.06
    _priority
    0.06
     ├
    0.06
     INCLUDE
    0.06
     privile
    0.06
     関連
    0.06
     RemoteException
    0.05
    Act Density 0.026%

    No Known Activations