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

    Neuronpedia

    INDEX
    Explanations

    small sizes or quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ড্রিম
    0.51
     ሞ
    0.47
    ontiti
    0.46
    이트
    0.46
    니다
    0.46
    ิด
    0.45
     ідэ
    0.44
    GINIA
    0.44
     자연
    0.43
    هِ
    0.42
    POSITIVE LOGITS
    concatenate
    0.41
     küçük
    0.41
    集中
    0.40
     piccoli
    0.40
     pequeno
    0.40
    符合
    0.39
     Korn
    0.38
     concatenate
    0.38
     einzel
    0.38
     continuación
    0.38
    Act Density 0.002%

    No Known Activations