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

    Neuronpedia

    INDEX
    Explanations

    one word in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    씩
    0.82
     jeweiligen
    0.79
    就行
    0.79
     потрі
    0.77
     Qxc
    0.73
     стороны
    0.72
    ቹን
    0.71
     gewisse
    0.70
    acf
    0.70
     demais
    0.69
    POSITIVE LOGITS
     one
    3.09
     یکی
    2.93
     одним
    2.51
     salah
    2.44
     among
    2.42
     arguably
    2.40
     yksi
    2.34
     jedną
    2.32
     одной
    2.31
    Among
    2.30
    Act Density 1.522%

    No Known Activations