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

    Neuronpedia

    INDEX
    Explanations

    addresses and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     giver
    -1.34
    焢
    -1.31
     安装
    -1.26
    糴
    -1.25
    鱻
    -1.25
    ⇩
    -1.23
     新款
    -1.23
     抠
    -1.20
    ientos
    -1.19
    Карьера
    -1.19
    POSITIVE LOGITS
     in
    1.73
     It
    1.48
     Also
    1.42
     You
    1.25
     just
    1.21
     much
    1.20
    ;
    1.19
     mė
    1.18
     What
    1.18
     time
    1.18
    Act Density 0.075%

    No Known Activations