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

    Neuronpedia

    INDEX
    Explanations

    numerical and technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ld
    -0.07
    enství
    -0.07
     Adapt
    -0.06
    ocols
    -0.06
    -img
    -0.06
    าส
    -0.06
    .layers
    -0.06
     blev
    -0.06
    Stick
    -0.06
    _sales
    -0.06
    POSITIVE LOGITS
     types
    0.07
     aşağı
    0.07
     guarante
    0.07
     (...)
    0.07
     //!
    0.07
     SEA
    0.06
     Juan
    0.06
    .Large
    0.06
     Legislation
    0.06
    .DoesNotExist
    0.06
    Act Density 0.000%

    No Known Activations