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

    Neuronpedia

    INDEX
    Explanations

    Watermarking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    yu
    -0.07
     outings
    -0.06
     opción
    -0.06
     cbo
    -0.06
     conte
    -0.06
     multiples
    -0.06
     feasibility
    -0.06
    /con
    -0.06
     Lyon
    -0.06
     probl
    -0.06
    POSITIVE LOGITS
     watermark
    0.11
    =forms
    0.08
     Searching
    0.07
    .text
    0.07
     Songs
    0.07
     sahip
    0.07
     Maximum
    0.07
    Water
    0.06
     Wei
    0.06
     навч
    0.06
    Act Density 0.001%

    No Known Activations