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

    Neuronpedia

    INDEX
    Explanations

    forms of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ゎ
    0.35
     ид
    0.34
    Tenemos
    0.34
     জীবনের
    0.34
    🧒
    0.34
     માતા
    0.33
     Также
    0.33
     рођено
    0.33
     માટે
    0.33
     Европа
    0.33
    POSITIVE LOGITS
     unmittelbar
    0.36
     সম্ভবত
    0.35
     przedsi
    0.33
     discretionary
    0.32
     hipot
    0.29
     discernible
    0.29
    ᡠ
    0.29
     अपेक्षाकृत
    0.29
     wrench
    0.28
     निर्धारण
    0.28
    Act Density 0.000%

    No Known Activations