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

    Neuronpedia

    INDEX
    Explanations

    baseball, hold, today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ant
    0.39
     عنا
    0.38
    㶱
    0.37
     आरमार
    0.36
     вершин
    0.36
     Newborn
    0.36
     beats
    0.36
     অবি
    0.36
     حرام
    0.35
     peck
    0.35
    POSITIVE LOGITS
    Op
    0.43
    Miss
    0.43
    Sele
    0.40
    selector
    0.40
    ítani
    0.39
    Giải
    0.39
    Política
    0.39
    Selector
    0.39
    Hö
    0.38
    Das
    0.38
    Act Density 0.004%

    No Known Activations