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

    Neuronpedia

    INDEX
    Explanations

    but in other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    provides
    0.51
    மைய
    0.49
     Facilities
    0.49
    took
    0.46
    tuvo
    0.45
     করছিল
    0.45
    ensure
    0.45
     both
    0.44
     permitió
    0.44
     Forms
    0.43
    POSITIVE LOGITS
     אבל
    0.69
     ولكن
    0.69
     แต่
    0.66
     ngunit
    0.63
     لكن
    0.62
    하지만
    0.60
     nhưng
    0.58
     但是
    0.57
    แต่
    0.57
     lakini
    0.55
    Act Density 0.005%

    No Known Activations