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

    Neuronpedia

    INDEX
    Explanations

    seeking immediate help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     👌
    0.52
     เนาะ
    0.50
     মজার
    0.47
    ちょっと
    0.47
     nifty
    0.47
     ;)
    0.45
    하기도
    0.45
     слегка
    0.45
     comfy
    0.45
    Occasionally
    0.44
    POSITIVE LOGITS
     immediately
    1.80
     IMMEDI
    1.80
     urgently
    1.79
     imediatamente
    1.59
     Immediately
    1.56
     immédiatement
    1.55
    immediately
    1.53
    Immediately
    1.51
     immedi
    1.50
     immediatamente
    1.50
    Act Density 0.093%

    No Known Activations