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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    ítulo
    -0.07
     vier
    -0.06
     mots
    -0.06
     �
    -0.06
    akh
    -0.06
     wit
    -0.06
    /xml
    -0.06
     XMLHttpRequest
    -0.06
    irms
    -0.06
    POSITIVE LOGITS
     embroidery
    0.07
    Lite
    0.07
     řekl
    0.06
    .today
    0.06
     nudity
    0.06
     renting
    0.06
     спеці
    0.06
     Japanese
    0.06
    ?</
    0.06
     Armed
    0.05
    Act Density 0.023%

    No Known Activations