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

    Neuronpedia

    INDEX
    Explanations

    I was + verb-ing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    निष्कर्ष
    0.83
     irreducible
    0.81
     ধীরে
    0.79
     encontrados
    0.77
     सीखा
    0.76
     discernible
    0.75
    随时
    0.75
     menambah
    0.74
     फैलता
    0.74
     solvable
    0.74
    POSITIVE LOGITS
     wondering
    1.49
     hoping
    1.39
     thinking
    1.26
     curious
    1.06
    Wonder
    1.06
    thinking
    1.05
     reading
    1.05
     pondering
    1.05
     Hoping
    1.05
     expecting
    1.02
    Act Density 0.039%

    No Known Activations