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

    Neuronpedia

    INDEX
    Explanations

    names or parts of names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Niger
    0.32
    Nigerian
    0.29
     Magistrate
    0.29
     Igbo
    0.29
     депута
    0.26
     Zanu
    0.26
    ार्म
    0.26
     Nigerians
    0.26
     Yoruba
    0.26
    💁
    0.26
    POSITIVE LOGITS
     and
    0.45
     for
    0.31
     மற்றும்
    0.29
    +
    0.29
     &
    0.29
     data
    0.28
     research
    0.28
    และการ
    0.28
     yoga
    0.27
     or
    0.27
    Act Density 0.001%

    No Known Activations