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

    Neuronpedia

    INDEX
    Explanations

    code commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrangement
    -0.08
     innan
    -0.08
     Arrangement
    -0.07
     Bank
    -0.07
     Stats
    -0.07
     procl
    -0.07
     creada
    -0.07
     cartão
    -0.07
     intercept
    -0.07
    gf
    -0.07
    POSITIVE LOGITS
     Repairs
    0.08
    _CONFIG
    0.08
     repairs
    0.08
    _SM
    0.08
     fractured
    0.08
     Rosen
    0.08
     Yok
    0.08
    anean
    0.07
     unprecedented
    0.07
     Гол
    0.07
    Act Density 0.005%

    No Known Activations