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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     موضوع
    -0.07
     다시
    -0.07
    .just
    -0.06
    semi
    -0.06
    ρή
    -0.06
     propag
    -0.06
    stras
    -0.06
    .major
    -0.06
     Περι
    -0.06
    .mi
    -0.06
    POSITIVE LOGITS
    Profiler
    0.07
    _RPC
    0.07
    %;"
    0.07
     ↵    ↵
    0.06
    ,↵↵↵↵
    0.06
    вок
    0.06
    [l
    0.06
     --------------------------------------------------------------------------↵
    0.06
    @endif
    0.06
    自动
    0.06
    Act Density 0.063%

    No Known Activations