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

    Neuronpedia

    INDEX
    Explanations

    90

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     груд
    -0.07
    us
    -0.07
     defiance
    -0.07
     photons
    -0.07
     setContent
    -0.06
     artifacts
    -0.06
     bron
    -0.06
     creado
    -0.06
     Dexter
    -0.06
    chia
    -0.06
    POSITIVE LOGITS
    45
    0.08
    mobile
    0.08
    90
    0.08
    Paths
    0.07
    巴
    0.07
     safer
    0.07
     사람
    0.07
    PS
    0.07
    091
    0.07
     "/"↵
    0.07
    Act Density 0.019%

    No Known Activations