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

    Neuronpedia

    INDEX
    Explanations

    position: fixed;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.35
     Geographic
    0.32
     корреспонд
    0.31
     cardiomy
    0.30
     boomers
    0.30
    τικές
    0.30
     spouse
    0.30
     incub
    0.29
    0.29
     geographic
    0.29
    POSITIVE LOGITS
     kasut
    0.38
     palju
    0.38
    结局
    0.38
     wartość
    0.37
    untuk
    0.36
     AppMethodBeat
    0.35
    ലോക
    0.35
    可爱
    0.35
     jika
    0.35
    ğer
    0.34
    Act Density 0.002%

    No Known Activations