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

    Neuronpedia

    INDEX
    Explanations

    relationships and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stills
    0.48
     features
    0.44
     follow
    0.42
     tun
    0.42
     reminiscent
    0.41
     projects
    0.41
     developing
    0.41
     alleviating
    0.41
     family
    0.40
     impulses
    0.40
    POSITIVE LOGITS
    Answer
    0.49
    どのように
    0.46
    powied
    0.44
     ऑप्शन
    0.42
    Explanation
    0.42
     প্রকার
    0.42
     ተግባ
    0.42
    வ்வேறு
    0.41
     explicação
    0.41
     الاجابه
    0.40
    Act Density 0.000%

    No Known Activations