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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     USERS
    -0.06
    nP
    -0.06
     VAL
    -0.06
     мист
    -0.06
     barber
    -0.06
    @Resource
    -0.06
    .favorite
    -0.06
     reelection
    -0.06
     internacional
    -0.06
     ironically
    -0.06
    POSITIVE LOGITS
    agit
    0.08
    ickness
    0.07
     union
    0.06
     contention
    0.06
    programming
    0.06
    aes
    0.06
     hans
    0.06
     sadness
    0.06
     surprise
    0.06
     kay
    0.06
    Act Density 0.003%

    No Known Activations