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

    Neuronpedia

    INDEX
    Explanations

    fitting and matching contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሳሪያ
    0.72
     întreb
    0.61
    殳
    0.60
    ્સ
    0.57
    ప్రత్యర్థి
    0.57
    t
    0.56
     informée
    0.55
    界的
    0.54
    MEX
    0.54
    Ꮐ
    0.54
    POSITIVE LOGITS
    ،
    0.96
    ，
    0.83
     snugly
    0.80
    into
    0.77
    ра
    0.67
     इनटू
    0.67
    다
    0.66
    、
    0.65
    ying
    0.64
    olar
    0.64
    Act Density 0.036%

    No Known Activations