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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     به
    -0.07
    �
    -0.07
    掛
    -0.06
     Jacksonville
    -0.06
     ->↵
    -0.06
    まま
    -0.06
    dust
    -0.06
     watermark
    -0.06
     Ethnic
    -0.06
     hott
    -0.06
    POSITIVE LOGITS
     Flake
    0.07
    lat
    0.07
    атків
    0.06
     peoples
    0.06
    ублі
    0.06
     Justice
    0.06
     فض
    0.06
    ::::::::
    0.06
    ouis
    0.06
     explosive
    0.06
    Act Density 0.153%

    No Known Activations