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

    Neuronpedia

    INDEX
    Explanations

    presented

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roads
    -0.07
    akin
    -0.06
     llvm
    -0.06
    ména
    -0.06
    acción
    -0.06
    сторія
    -0.06
     thaimassage
    -0.06
    strukce
    -0.06
    akte
    -0.06
    FolderPath
    -0.06
    POSITIVE LOGITS
    Exposed
    0.08
     assertNotNull
    0.06
    ＠
    0.06
     presenting
    0.06
     subscribe
    0.06
     بخ
    0.06
     presented
    0.06
    原
    0.06
    Lexer
    0.06
     failure
    0.06
    Act Density 0.007%

    No Known Activations