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

    Neuronpedia

    INDEX
    Explanations

    Minimal API, systems, job, Year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    西
    0.52
    ë
    0.42
    Western
    0.42
    lim
    0.41
     Aus
    0.41
    Sie
    0.41
     sie
    0.40
    WEST
    0.40
    Deux
    0.40
     Bildschirm
    0.40
    POSITIVE LOGITS
     стаўкі
    0.56
     CFO
    0.53
     งวด
    0.53
     акча
    0.49
     धन
    0.48
     DURING
    0.48
     APIDC
    0.48
     ชีวิต
    0.48
    দ্দিন
    0.47
     lucrative
    0.47
    Act Density 0.000%

    No Known Activations