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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     southwest
    -0.07
     parse
    -0.07
     Labels
    -0.06
     Expansion
    -0.06
     cí
    -0.06
     Behaviour
    -0.06
    �
    -0.06
     stories
    -0.06
    ticks
    -0.06
    613
    -0.06
    POSITIVE LOGITS
     uy
    0.07
    oso
    0.06
    .numberOfLines
    0.06
     mọi
    0.06
    .RELATED
    0.06
     Reeves
    0.06
    ốc
    0.06
    ानन
    0.06
     PCIe
    0.06
    =msg
    0.06
    Act Density 0.024%

    No Known Activations