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

    Neuronpedia

    INDEX
    Explanations

    installing software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diversi
    1.18
     pong
    1.17
     cuarto
    1.16
    매
    1.13
    ெட்
    1.11
    صوص
    1.11
     besieged
    1.10
    わけで
    1.06
    ^{-}$
    1.06
    鋒
    1.06
    POSITIVE LOGITS
    tion
    1.42
    tired
    1.42
    ج
    1.37
    ся
    1.36
     therefrom
    1.31
     ráp
    1.29
    な
    1.28
    yaxis
    1.28
    ї
    1.26
    যুব
    1.24
    Act Density 0.089%

    No Known Activations