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

    Neuronpedia

    INDEX
    Explanations

    i cannot

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wide
    0.79
     Ties
    0.76
     گوش
    0.74
     Phil
    0.72
     Universal
    0.72
    天的
    0.72
     Dana
    0.71
    ske
    0.71
    資本
    0.70
     ইন্টার
    0.70
    POSITIVE LOGITS
     cannot
    1.22
     understand
    1.12
    cannot
    1.02
     compreender
    0.97
     understood
    0.86
     can
    0.85
     quadrado
    0.83
     cant
    0.83
    understand
    0.83
     comprendre
    0.81
    Act Density 0.024%

    No Known Activations