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

    Neuronpedia

    INDEX
    Explanations

    ever written

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diese
    1.13
    Dieser
    1.00
    Unser
    1.00
    Creates
    0.94
     eben
    0.89
    SINGLE
    0.89
    Deutschland
    0.87
    \*
    0.86
     Pflanzen
    0.85
    Perfil
    0.84
    POSITIVE LOGITS
    ič
    1.04
    λια
    0.87
    ಿದ
    0.85
    oys
    0.83
    ections
    0.82
    oucher
    0.82
    iš
    0.81
     Vitamins
    0.81
     CCI
    0.80
    нии
    0.80
    Act Density 0.000%

    No Known Activations