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

    Neuronpedia

    INDEX
    Explanations

    sentence packs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IMO
    0.46
    দেশের
    0.44
     IMHO
    0.44
     resemble
    0.42
     deck
    0.42
     hegemony
    0.42
     IMAGE
    0.41
     zemlji
    0.40
     resembling
    0.40
    ન્મ
    0.40
    POSITIVE LOGITS
    You
    0.45
     겨
    0.44
    ста
    0.39
    RAM
    0.38
    STON
    0.38
    ４
    0.37
     মিয়া
    0.36
    ellas
    0.36
     tình
    0.35
    Sto
    0.35
    Act Density 0.001%

    No Known Activations