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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     št
    -0.07
     yıllar
    -0.07
     Мак
    -0.06
    MI
    -0.06
     LORD
    -0.06
    }$/
    -0.06
     Πο
    -0.06
     det
    -0.06
     uncomfort
    -0.06
     Nah
    -0.06
    POSITIVE LOGITS
     utilis
    0.07
    aires
    0.06
    .address
    0.06
     controlId
    0.06
    prev
    0.06
    ITIONS
    0.06
     rampant
    0.06
    .Magic
    0.06
     ITE
    0.06
     blitz
    0.06
    Act Density 0.018%

    No Known Activations