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

    Neuronpedia

    INDEX
    Explanations

    Jet configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     часто
    -0.07
    choose
    -0.06
    (js
    -0.06
    323
    -0.06
    499
    -0.06
    /blue
    -0.06
    ][:
    -0.06
     renting
    -0.06
     Liste
    -0.06
    :error
    -0.06
    POSITIVE LOGITS
    işim
    0.07
     nuestros
    0.06
     em
    0.06
    ेखत
    0.06
     torrent
    0.06
    .duration
    0.06
     Rod
    0.06
    教师
    0.06
     Separate
    0.06
    efined
    0.06
    Act Density 0.025%

    No Known Activations