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

    Neuronpedia

    INDEX
    Explanations

    million

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perk
    -0.07
    这
    -0.07
     rio
    -0.06
     ALOG
    -0.06
     dogs
    -0.06
     surreal
    -0.06
     згад
    -0.06
     Croat
    -0.06
     Sik
    -0.06
     most
    -0.06
    POSITIVE LOGITS
     completes
    0.08
    の大
    0.07
    .jetbrains
    0.06
     isset
    0.06
     الملك
    0.06
    .yaml
    0.06
    groupId
    0.06
    _prep
    0.06
    -picker
    0.06
    ़े
    0.06
    Act Density 0.015%

    No Known Activations