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

    Neuronpedia

    INDEX
    Explanations

    various follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ஹா
    0.40
     fragmentation
    0.40
     intermin
    0.40
     никогда
    0.39
    დაც
    0.38
     watermelon
    0.38
    0.38
     দখল
    0.38
    Fragmentation
    0.37
    交通
    0.37
    POSITIVE LOGITS
    up
    0.41
    orders
    0.39
    эк
    0.39
    ares
    0.39
    ubah
    0.38
    olese
    0.38
    aud
    0.37
    ओके
    0.37
    leo
    0.37
    uaikan
    0.37
    Act Density 0.000%

    No Known Activations