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

    Neuronpedia

    INDEX
    Explanations

    Trying something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     redirects
    -0.07
     одерж
    -0.06
     continu
    -0.06
     presidents
    -0.06
     disponibles
    -0.06
     granularity
    -0.05
    _extension
    -0.05
    }};↵
    -0.05
     FONT
    -0.05
     RGBA
    -0.05
    POSITIVE LOGITS
    research
    0.07
     muht
    0.07
     warmer
    0.07
     Breaking
    0.07
     $
    0.07
     usefulness
    0.07
    etzt
    0.07
     reopening
    0.06
    izzer
    0.06
     Influ
    0.06
    Act Density 0.003%

    No Known Activations