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

    Neuronpedia

    INDEX
    Explanations

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Selecting
    -0.08
     вним
    -0.08
     wiring
    -0.07
    oan
    -0.07
     средств
    -0.07
     glance
    -0.07
     Vander
    -0.07
     aten
    -0.07
     обязан
    -0.07
     Martínez
    -0.07
    POSITIVE LOGITS
     iler
    0.09
     상승
    0.09
    ENSIONS
    0.08
     trovi
    0.08
     rolls
    0.08
    years
    0.08
     ush
    0.08
     Account
    0.08
     escorts
    0.08
     upgrading
    0.08
    Act Density 0.007%

    No Known Activations