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

    Neuronpedia

    INDEX
    Explanations

    Leonardo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     empowerment
    -0.09
     empowering
    -0.08
     Empower
    -0.08
    sexta
    -0.08
     silent
    -0.07
     cruel
    -0.07
     mandated
    -0.07
     entrepreneurship
    -0.07
     loudly
    -0.07
     loud
    -0.07
    POSITIVE LOGITS
     Tes
    0.08
    witter
    0.08
    adalafil
    0.08
     tensorflow
    0.08
     Photoshop
    0.08
     tes
    0.08
     Teller
    0.07
    antal
    0.07
     sap
    0.07
     dolgo
    0.07
    Act Density 0.004%

    No Known Activations