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

    Neuronpedia

    INDEX
    Explanations

    github repositories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    百
    -0.07
    وا
    -0.07
     HashSet
    -0.07
    akh
    -0.06
    ービ
    -0.06
     ferr
    -0.06
     divergence
    -0.06
    raně
    -0.06
    üç
    -0.06
    landing
    -0.06
    POSITIVE LOGITS
     compromised
    0.07
     staat
    0.06
     Export
    0.06
    phony
    0.06
    ookie
    0.06
     Heart
    0.06
     PEOPLE
    0.06
    anonymous
    0.06
    ebi
    0.06
     intentions
    0.06
    Act Density 0.065%

    No Known Activations