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

    Neuronpedia

    INDEX
    Explanations

    predicting probabilities or future outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    araham
    0.44
    Ⲗ
    0.40
     Froome
    0.39
     ಇದಕ್ಕೆ
    0.39
     ресу
    0.39
     malnourished
    0.39
    埛
    0.39
    ാവ്
    0.38
    ానిక
    0.37
     userInput
    0.37
    POSITIVE LOGITS
     مست
    0.41
    kład
    0.41
     kic
    0.39
    ulfill
    0.39
    去掉
    0.38
    uf
    0.38
    usp
    0.38
    UM
    0.38
    usted
    0.38
    ogo
    0.37
    Act Density 0.000%

    No Known Activations