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

    Neuronpedia

    INDEX
    Explanations

    what or why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     👍
    0.84
     cool
    0.82
     👌
    0.81
     how
    0.79
     Cool
    0.79
     maybe
    0.78
     কিছুটা
    0.78
    ക്കാം
    0.76
    cool
    0.75
     थोड़ा
    0.75
    POSITIVE LOGITS
     suddenly
    0.90
     provoked
    0.90
     собственно
    0.86
     roused
    0.81
     plötzlich
    0.81
     prompted
    0.79
     exactamente
    0.79
     derrière
    0.78
     Suddenly
    0.77
     вдруг
    0.74
    Act Density 0.192%

    No Known Activations