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

    Neuronpedia

    INDEX
    Explanations

    tell me, solve, translate, write

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    heartedly
    0.44
     చేసుకు
    0.44
     করেই
    0.44
     நிச்சயம்
    0.43
     drenched
    0.43
     👌
    0.43
     brewed
    0.43
    தமான
    0.42
     होकर
    0.42
    必ず
    0.42
    POSITIVE LOGITS
    하시오
    0.68
    시오
    0.67
    니다
    0.55
     및
    0.54
    ってください
    0.50
     문제입니다
    0.48
    세요
    0.48
    르
    0.47
     구
    0.46
    입니다
    0.46
    Act Density 0.001%

    No Known Activations