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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INY
    -0.07
    �合
    -0.07
     prosecute
    -0.07
     �
    -0.07
    SPORT
    -0.07
    .appspot
    -0.07
    ровер
    -0.07
    tearDown
    -0.07
    レビ
    -0.07
     abdominal
    -0.06
    POSITIVE LOGITS
    añ
    0.07
    aç
    0.06
    ，与
    0.06
     Marsh
    0.06
    Als
    0.06
     eksik
    0.06
     Currently
    0.06
    -fire
    0.06
     населення
    0.06
     discrepan
    0.06
    Act Density 0.028%

    No Known Activations