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

    Neuronpedia

    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    another
    -0.06
    _a
    -0.06
    phot
    -0.06
     digitally
    -0.06
    ?>/
    -0.06
     Lily
    -0.05
     ons
    -0.05
    animals
    -0.05
    “A
    -0.05
     españ
    -0.05
    POSITIVE LOGITS
     wildfires
    0.08
     expelled
    0.08
     Accent
    0.07
    orrh
    0.07
    ching
    0.07
     στον
    0.07
    英语
    0.07
     retrofit
    0.07
    ทำ
    0.07
    .scope
    0.07
    Act Density 0.002%

    No Known Activations