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

    Neuronpedia

    INDEX
    Explanations

    jobs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ded
    -0.07
    ОС
    -0.07
    особ
    -0.07
    出资
    -0.07
     Tops
    -0.07
     ling
    -0.07
    _resources
    -0.07
    -dot
    -0.07
    있
    -0.07
    캑
    -0.06
    POSITIVE LOGITS
    _MANY
    0.07
    .live
    0.07
     availability
    0.07
    :absolute
    0.07
    icipant
    0.07
    Bah
    0.07
     vintage
    0.07
    .Absolute
    0.07
     davon
    0.07
    %"
    0.07
    Act Density 0.070%

    No Known Activations