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

    Neuronpedia

    INDEX
    Explanations

    various language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    color
    0.47
    High
    0.41
    Color
    0.41
    Colorado
    0.39
    色が
    0.38
     Lowe
    0.38
    aney
    0.38
    が高
    0.38
    high
    0.37
    into
    0.37
    POSITIVE LOGITS
    స్క
    0.44
     پروگرام
    0.41
     módulos
    0.40
    尔多
    0.40
     времена
    0.39
     arrond
    0.38
    ักษณะ
    0.38
    VERNMENT
    0.38
     eggs
    0.37
     рис
    0.37
    Act Density 0.000%

    No Known Activations