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

    Neuronpedia

    INDEX
    Explanations

    media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     battery
    -0.07
    .unlock
    -0.07
    yt
    -0.07
    -touch
    -0.06
    реп
    -0.06
     dismant
    -0.06
    -find
    -0.06
     giving
    -0.06
    谓
    -0.06
     prest
    -0.06
    POSITIVE LOGITS
     MEDIA
    0.07
    Rose
    0.07
     병
    0.07
     fim
    0.06
     Media
    0.06
     Pol
    0.06
     Craigslist
    0.06
     Luo
    0.06
    brick
    0.06
     dresser
    0.06
    Act Density 0.015%

    No Known Activations