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

    Neuronpedia

    INDEX
    Explanations

    do you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    โร
    0.70
    ۣ
    0.69
     lark
    0.60
    ብስ
    0.58
    ertime
    0.57
     लागेल
    0.56
    Vent
    0.56
     कोर्ट
    0.55
     लंबी
    0.55
    Ore
    0.55
    POSITIVE LOGITS
     میرے
    0.71
     സമീപ
    0.68
    юсь
    0.68
     rest
    0.66
     weaknesses
    0.65
     rests
    0.65
     שלי
    0.63
    celli
    0.63
     feels
    0.63
     explicación
    0.63
    Act Density 0.094%

    No Known Activations