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

    Neuronpedia

    INDEX
    Explanations

    coverage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     halt
    -0.07
    солют
    -0.07
     jylland
    -0.07
    _PUSH
    -0.07
    istro
    -0.06
     &$
    -0.06
    elter
    -0.06
    átu
    -0.06
    czas
    -0.06
    оком
    -0.06
    POSITIVE LOGITS
     Pic
    0.07
     solids
    0.06
    _)↵
    0.06
     investigación
    0.06
    acas
    0.06
    435
    0.06
    َد
    0.06
     Checkbox
    0.06
     Covent
    0.06
    NdEx
    0.06
    Act Density 0.001%

    No Known Activations