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

    Neuronpedia

    INDEX
    Explanations

    measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /utils
    -0.07
    example
    -0.07
     Berm
    -0.06
     січня
    -0.06
     Lag
    -0.06
     statute
    -0.06
    594
    -0.06
    540
    -0.06
     mega
    -0.06
     йому
    -0.06
    POSITIVE LOGITS
     sesso
    0.08
     famil
    0.07
    Qui
    0.06
     insecurity
    0.06
    όγ
    0.06
     baskı
    0.06
    ασία
    0.06
    .terminate
    0.06
    ’deki
    0.06
     �
    0.06
    Act Density 0.033%

    No Known Activations