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

    Neuronpedia

    INDEX
    Explanations

    drinks and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਅਤੇ
    0.53
     തന്റെ
    0.46
     καὶ
    0.46
     წლის
    0.46
    はなく
    0.45
     आणि
    0.43
     அல்லது
    0.43
     эшлә
    0.42
     menikah
    0.41
     своих
    0.41
    POSITIVE LOGITS
     beverage
    0.41
     Cartoon
    0.40
     dye
    0.40
     on
    0.39
     sauf
    0.39
     carton
    0.38
     all
    0.38
     Chicken
    0.38
     assault
    0.38
     ballots
    0.38
    Act Density 0.008%

    No Known Activations