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

    Neuronpedia

    INDEX
    Explanations

    Code/Various languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    あげ
    -0.07
    .await
    -0.07
     kaufen
    -0.06
     вд
    -0.06
     potrav
    -0.06
     відсут
    -0.06
     зазнач
    -0.06
    ุง
    -0.06
    kel
    -0.06
     Bru
    -0.06
    POSITIVE LOGITS
    想
    0.06
     threads
    0.06
     stakes
    0.06
     Jefferson
    0.06
    Н
    0.06
     exclusion
    0.06
    Define
    0.06
     directly
    0.06
    ERIC
    0.06
    lood
    0.06
    Act Density 0.000%

    No Known Activations