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

    Neuronpedia

    INDEX
    Explanations

    Google

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marine
    -0.06
     Dispatcher
    -0.06
     psychiat
    -0.06
    ircraft
    -0.06
     remar
    -0.06
    878
    -0.06
    fname
    -0.06
    乳
    -0.06
     flux
    -0.06
    ccb
    -0.06
    POSITIVE LOGITS
     Google
    0.13
    Google
    0.11
     google
    0.09
     GOOGLE
    0.08
    google
    0.07
    oogle
    0.07
    (il
    0.07
    .eu
    0.07
    /table
    0.07
    too
    0.07
    Act Density 0.016%

    No Known Activations