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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iva
    -0.08
    IVA
    -0.07
    posite
    -0.07
     besonders
    -0.07
     affid
    -0.06
     koş
    -0.06
    itive
    -0.06
     uphill
    -0.06
     heroine
    -0.06
    .backend
    -0.06
    POSITIVE LOGITS
    acz
    0.06
    eller
    0.06
     gag
    0.06
    ([...
    0.06
    ทร
    0.06
     dram
    0.06
     Icons
    0.06
     возмож
    0.06
     userEmail
    0.06
    ,\"
    0.06
    Act Density 0.000%

    No Known Activations