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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worse
    -0.08
     vagina
    -0.07
     horrifying
    -0.07
    yty
    -0.07
     Fn
    -0.07
    .im
    -0.07
    -0.07
     irres
    -0.07
     шк
    -0.07
     subscriptions
    -0.07
    POSITIVE LOGITS
     contemplation
    0.10
     solitude
    0.09
    ಗಿನ
    0.09
     contempl
    0.09
     homage
    0.09
     শান্ত
    0.09
     悠
    0.09
     loneliness
    0.09
     serenity
    0.09
     twilight
    0.09
    Act Density 0.009%
    No Known Activations