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

    Neuronpedia

    INDEX
    Explanations

    optimal conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    worth
    0.78
     tellement
    0.76
     Algun
    0.74
     humbly
    0.71
    र्जी
    0.71
     형태로
    0.71
    ॉर्म
    0.70
     worth
    0.66
     WORTH
    0.66
     отдельно
    0.66
    POSITIVE LOGITS
     maximum
    2.51
     максима
    2.21
    maximum
    2.18
     maximale
    2.09
     optimum
    2.09
     Maximum
    2.01
     optimal
    2.00
     utmost
    1.99
    Maximum
    1.97
     maximal
    1.91
    Act Density 0.991%

    No Known Activations