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

    Neuronpedia

    INDEX
    Explanations

    planned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    😊
    -0.08
     bitcoins
    -0.08
     Invest
    -0.08
    special
    -0.08
     tinc
    -0.08
     janvier
    -0.08
     expensive
    -0.08
    .pem
    -0.08
     juin
    -0.08
     siyas
    -0.08
    POSITIVE LOGITS
    istema
    0.08
     targeting
    0.08
     Alpine
    0.08
    LH
    0.08
     वातावरण
    0.08
     અંત
    0.08
     living
    0.08
    ТР
    0.08
     प्रणाली
    0.08
     samenleving
    0.08
    Act Density 0.003%

    No Known Activations