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

    Neuronpedia

    INDEX
    Explanations

    Java code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comput
    -0.06
    щего
    -0.06
     goddess
    -0.06
    Cog
    -0.06
     loc
    -0.06
     автор
    -0.06
     �
    -0.06
    bole
    -0.06
    夜
    -0.06
    她的
    -0.06
    POSITIVE LOGITS
    건
    0.07
     consum
    0.07
    (register
    0.06
    mland
    0.06
     ближ
    0.06
    oeff
    0.06
     건
    0.06
    updating
    0.06
    /find
    0.06
    مي
    0.06
    Act Density 0.003%

    No Known Activations