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

    Neuronpedia

    INDEX
    Explanations

    certainly derivatives product Bell hardware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innego
    0.41
     BoxFit
    0.41
     nowego
    0.40
     inflict
    0.39
     Sof
    0.38
    щиков
    0.38
    벽
    0.38
    榎
    0.37
    طور
    0.37
     hypergly
    0.37
    POSITIVE LOGITS
    defer
    0.38
    oitte
    0.37
    鑫
    0.37
     دخول
    0.37
    dest
    0.36
     jay
    0.36
     də
    0.36
    xhr
    0.36
    $/
    0.36
     serial
    0.35
    Act Density 0.000%

    No Known Activations