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

    Neuronpedia

    INDEX
    Explanations

    likely sometime early

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꭻ
    0.44
    Tenemos
    0.43
     crecer
    0.42
    RICK
    0.42
     मिट
    0.41
     anagram
    0.41
     decrement
    0.39
     caballo
    0.39
     molasses
    0.39
    િક્
    0.38
    POSITIVE LOGITS
     solidarity
    0.44
     intended
    0.41
     नेत्र
    0.40
     державних
    0.39
    during
    0.37
     شاء
    0.37
     계획
    0.37
    planned
    0.36
    intended
    0.36
     contributions
    0.36
    Act Density 0.007%

    No Known Activations