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

    Neuronpedia

    INDEX
    Explanations

    Math/Algebra Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     চাল
    -0.08
     veril
    -0.08
    рақ
    -0.08
    талған
    -0.08
     DK
    -0.08
     çalış
    -0.07
    ítás
    -0.07
    .Documents
    -0.07
     এক
    -0.07
    ltk
    -0.07
    POSITIVE LOGITS
     m
    0.08
    _COMPONENT
    0.08
    ')
↵
    0.08
    }")
↵
    0.08
    },
↵
    0.07
     presentatie
    0.07
    Bem
    0.07
     Hamp
    0.07
    presentation
    0.07
     Daarbij
    0.07
    Act Density 0.169%

    No Known Activations