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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PRES
    -0.07
     Billion
    -0.06
     cartridges
    -0.06
     вплив
    -0.06
    共和国
    -0.06
     anticip
    -0.06
     Governors
    -0.06
     hovering
    -0.06
    架
    -0.06
     utility
    -0.06
    POSITIVE LOGITS
    Thor
    0.07
    {
↵
↵
    0.07
     yıllarda
    0.07
     christmas
    0.07
    blah
    0.07
    ibi
    0.07
    řeba
    0.06
    рич
    0.06
     roce
    0.06
     habe
    0.06
    Act Density 0.018%

    No Known Activations