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

    Neuronpedia

    INDEX
    Explanations

    paste it here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tannins
    1.11
     vesicles
    1.09
     qubits
    1.09
    ം
    1.08
     phonons
    1.05
    ्स
    1.02
    }}}\
    1.00
    સર
    1.00
     adsorb
    0.99
     discourses
    0.98
    POSITIVE LOGITS
     وهذه
    1.07
     وهذا
    0.89
    -
    0.84
    ik
    0.80
    d
    0.80
    ian
    0.79
     accanto
    0.79
     unable
    0.77
    rance
    0.76
    built
    0.75
    Act Density 0.152%

    No Known Activations