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

    Neuronpedia

    INDEX
    Explanations

    executives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Garden
    -0.07
     Painter
    -0.06
     página
    -0.06
     Publication
    -0.06
     />
    -0.06
     poverty
    -0.06
     品
    -0.06
    olor
    -0.06
     garden
    -0.06
     tedious
    -0.06
    POSITIVE LOGITS
     executives
    0.25
     executive
    0.08
    icorn
    0.07
    CALL
    0.06
    gf
    0.06
     selections
    0.06
    Security
    0.06
     Executive
    0.06
    .Safe
    0.06
    (asset
    0.06
    Act Density 0.006%

    No Known Activations