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

    Neuronpedia

    INDEX
    Explanations

    project details and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    renzia
    0.51
    hattim
    0.50
    daki
    0.49
     forcément
    0.49
    antwoord
    0.48
    GEBURTS
    0.48
    álen
    0.47
     dajj
    0.47
    ifrån
    0.46
    gült
    0.46
    POSITIVE LOGITS
    \}
    0.52
     آغاز
    0.50
    开始
    0.49
     시작
    0.47
     Successful
    0.46
     Owl
    0.46
     ξεκ
    0.46
     successful
    0.44
     началом
    0.44
    大学
    0.44
    Act Density 0.004%

    No Known Activations