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

    Neuronpedia

    INDEX
    Explanations

    input shape specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SB
    0.39
     jüng
    0.39
    UMENT
    0.38
    덱
    0.38
    ペア
    0.38
     çiçek
    0.37
    蘭
    0.37
    
    0.37
     프랑
    0.36
    CVE
    0.36
    POSITIVE LOGITS
     느껴
    0.40
    قاف
    0.39
    andering
    0.39
    스터
    0.39
     مجموع
    0.38
    LogProfile
    0.37
    DateField
    0.37
     buffering
    0.37
     ስለ
    0.36
    Started
    0.36
    Act Density 0.000%

    No Known Activations