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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sınıf
    -0.07
    Returned
    -0.07
     Herald
    -0.06
    Cmd
    -0.06
     MRI
    -0.06
    Sky
    -0.06
     compile
    -0.06
    Fully
    -0.06
    _BUF
    -0.06
     baptized
    -0.06
    POSITIVE LOGITS
     dramatic
    0.07
    wash
    0.07
     Dimension
    0.07
    	group
    0.06
     photoc
    0.06
    elman
    0.06
    _weight
    0.06
     adorable
    0.06
     Again
    0.06
     weighting
    0.06
    Act Density 0.007%

    No Known Activations