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

    Neuronpedia

    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    can
    0.84
     asked
    0.82
     can
    0.82
    elni
    0.81
     চেয়ে
    0.80
    ionalmente
    0.80
    cursion
    0.80
     could
    0.80
    could
    0.78
    Puede
    0.78
    POSITIVE LOGITS
     внутри
    1.19
     желез
    1.07
    спе
    1.06
    бив
    1.06
     вести
    1.04
     внутріш
    1.03
     درون
    1.03
     координа
    1.00
     отече
    1.00
    耸
    0.99
    Act Density 0.009%

    No Known Activations