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

    Neuronpedia

    INDEX
    Explanations

    removing functionality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approves
    -0.07
    pizza
    -0.07
    _tm
    -0.07
    Approved
    -0.06
    .ph
    -0.06
     Handling
    -0.06
     PartialEq
    -0.06
     dom
    -0.06
    ,e
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    _Display
    0.07
    grounds
    0.07
     тобі
    0.07
     ABS
    0.06
    LOAT
    0.06
     UIImageView
    0.06
     ObjectOutputStream
    0.06
    acid
    0.06
     تلویزیون
    0.06
    (nameof
    0.06
    Act Density 0.002%

    No Known Activations