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

    Neuronpedia

    INDEX
    Explanations

    demonstration purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     organismo
    1.23
    醂
    1.12
    蜍
    1.12
     cynical
    1.11
     了
    1.05
     insulting
    1.05
     embarrass
    1.04
     granularity
    1.03
     bitters
    1.02
     пород
    1.01
    POSITIVE LOGITS
    ća
    1.13
     spust
    1.13
    ède
    1.13
    sla
    1.09
     ś
    1.08
     keď
    1.06
    чны
    1.06
    ič
    1.04
    żeń
    1.00
    inį
    1.00
    Act Density 0.000%

    No Known Activations