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

    Neuronpedia

    INDEX
    Explanations

    warrants or promises

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ن
    1.20
    ش
    1.13
     جنوب
    1.13
    いた
    1.09
    𝗯
    1.09
    نا
    1.09
    ز
    1.07
    ナ
    1.07
     বিশ্বকাপ
    1.06
     ش
    1.05
    POSITIVE LOGITS
    .
    1.27
    ,
    1.15
    :
    1.12
     eller
    1.06
     pursuant
    1.02
    ?
    1.01
     any
    0.97
     sådan
    0.96
     duly
    0.95
     offent
    0.92
    Act Density 0.294%

    No Known Activations