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

    Neuronpedia

    INDEX
    Explanations

    enforcement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ksi
    -0.07
    ili
    -0.07
     rua
    -0.07
    шел
    -0.07
     pé
    -0.07
    米
    -0.07
     sein
    -0.07
     pearls
    -0.06
    ousse
    -0.06
    차
    -0.06
    POSITIVE LOGITS
     salv
    0.08
     enforcement
    0.08
     elim
    0.07
     Sweep
    0.07
     граж
    0.06
     arma
    0.06
     adjustment
    0.06
    "}),↵
    0.06
     emanc
    0.06
    …the
    0.06
    Act Density 0.005%

    No Known Activations