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

    Neuronpedia

    INDEX
    Explanations

    uppercase letters, variables, equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     перспек
    0.32
     자신
    0.32
     प्रारूप
    0.31
    比亚
    0.31
     时尚
    0.31
    美好的
    0.31
     रिवाइज
    0.30
     جميل
    0.30
    签署
    0.30
     설명을
    0.30
    POSITIVE LOGITS
    T
    0.42
    F
    0.40
    8
    0.39
    G
    0.38
    6
    0.38
    B
    0.38
    K
    0.37
    V
    0.37
    f
    0.36
    N
    0.36
    Act Density 0.019%

    No Known Activations