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

    Neuronpedia

    INDEX
    Explanations

    without need or presence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ini
    0.40
    OY
    0.40
     Perf
    0.39
    জয়
    0.39
     ইমন
    0.38
     Callback
    0.37
    이라면
    0.37
     perfume
    0.37
     jj
    0.37
     perf
    0.36
    POSITIVE LOGITS
     મુ
    0.41
     difficoltà
    0.40
    льної
    0.39
    Metall
    0.39
     paucity
    0.38
    exceptions
    0.38
    हार
    0.37
     metallurgical
    0.37
    setzungen
    0.37
     depriving
    0.37
    Act Density 0.002%

    No Known Activations