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

    Neuronpedia

    INDEX
    Explanations

    training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ปล
    -0.07
    _initialized
    -0.06
    498
    -0.06
    GreaterThan
    -0.06
    .adj
    -0.06
    iqueta
    -0.06
    _pri
    -0.06
    FDA
    -0.06
    098
    -0.06
     finalize
    -0.05
    POSITIVE LOGITS
     tool
    0.07
     boutique
    0.07
     FOUR
    0.07
    /content
    0.07
     Crunch
    0.07
    Chrome
    0.07
     Helm
    0.07
     kommun
    0.07
     Cz
    0.07
     mấy
    0.07
    Act Density 0.010%

    No Known Activations