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

    Neuronpedia

    INDEX
    Explanations

    Legal/government documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    widget
    -0.07
    AndGet
    -0.07
     Thomson
    -0.07
     OPTION
    -0.07
     derivation
    -0.06
     Pager
    -0.06
     Sak
    -0.06
     DES
    -0.06
    посеред
    -0.06
     Lennon
    -0.06
    POSITIVE LOGITS
     breast
    0.07
     caffe
    0.06
     světa
    0.06
    рим
    0.06
     intensely
    0.06
     bishops
    0.06
    *****↵
    0.06
    fps
    0.06
    sweet
    0.05
    """,↵
    0.05
    Act Density 0.008%

    No Known Activations