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

    Neuronpedia

    INDEX
    Explanations

    break, open, potential, in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Τα
    0.84
    Ӯ
    0.78
    न्तर
    0.75
     Ouv
    0.74
    搪
    0.74
    मता
    0.71
     antifreeze
    0.71
     antifungal
    0.70
     élargies
    0.70
    Τα
    0.70
    POSITIVE LOGITS
    s
    0.90
    Sc
    0.79
    room
    0.77
    t
    0.77
    st
    0.74
    }):
    0.74
    ):
    0.73
     Just
    0.72
    )";
    0.71
    )").
    0.71
    Act Density 0.000%

    No Known Activations