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

    Neuronpedia

    INDEX
    Explanations

    importance of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dată
    0.52
     svojoj
    0.48
    ştik
    0.48
    cevam
    0.45
     የስ
    0.44
    modelLogin
    0.44
    lensFlare
    0.44
     الأحمر
    0.44
    ivă
    0.44
    abhavam
    0.43
    POSITIVE LOGITS
    t
    0.55
    '
    0.50
    istory
    0.49
     desde
    0.49
     erstellen
    0.47
     See
    0.47
    anged
    0.47
     barrel
    0.47
     Lawyer
    0.47
    k
    0.46
    Act Density 0.001%

    No Known Activations