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

    Neuronpedia

    INDEX
    Explanations

    radiologist, panic situation, Top AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     повинні
    0.80
    ك
    0.80
     ня
    0.79
    ↪
    0.77
     працю
    0.77
     тощо
    0.77
     meravigli
    0.76
     відповід
    0.76
     ефектив
    0.75
    णा
    0.75
    POSITIVE LOGITS
    u
    0.76
    álov
    0.69
    ওয়া
    0.68
    angleright
    0.67
     Первая
    0.64
    house
    0.64
     fakat
    0.64
    oš
    0.63
     tim
    0.63
    hedral
    0.63
    Act Density 0.001%

    No Known Activations