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

    Neuronpedia

    INDEX
    Explanations

    code and technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     걸
    -0.07
     공
    -0.07
    年に
    -0.07
     похож
    -0.07
     mens
    -0.07
    .ol
    -0.07
     Bronx
    -0.06
    elfast
    -0.06
    _IDS
    -0.06
    ]];
    -0.06
    POSITIVE LOGITS
     syscall
    0.07
     entrada
    0.07
     oldukça
    0.06
    STONE
    0.06
     hereby
    0.06
    (example
    0.06
     pueblo
    0.06
     lub
    0.06
    stone
    0.06
     Input
    0.06
    Act Density 0.000%

    No Known Activations