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

    Neuronpedia

    INDEX
    Explanations

    units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meiden
    -0.07
     pollen
    -0.06
     Mädchen
    -0.06
    _ctl
    -0.06
     церк
    -0.06
     cómo
    -0.06
     cheg
    -0.06
     sách
    -0.06
     ساده
    -0.06
    726
    -0.06
    POSITIVE LOGITS
    Methods
    0.07
     Stall
    0.07
     Dart
    0.07
    DR
    0.07
     Q
    0.07
    ush
    0.06
     ability
    0.06
     LES
    0.06
     ≤
    0.06
    ôte
    0.06
    Act Density 0.000%

    No Known Activations