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

    Neuronpedia

    INDEX
    Explanations

    creating strategy or useful properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    1.24
    e
    1.16
     signs
    1.12
    지
    1.10
    on
    1.09
     develop
    1.02
     leaps
    1.01
     signes
    0.98
     오히려
    0.96
     unemployment
    0.96
    POSITIVE LOGITS
    tembre
    1.44
    ১৪
    1.36
    ordable
    1.33
     appellees
    1.30
    ZUKI
    1.26
    笞
    1.25
     цей
    1.24
    ۚ
    1.24
    ⑰
    1.23
    鸯
    1.23
    Act Density 0.001%

    No Known Activations