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

    Neuronpedia

    INDEX
    Explanations

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਾ
    0.45
    issory
    0.41
    ้ํา
    0.39
    іо
    0.38
    autiful
    0.38
    ਓ
    0.37
    0.37
    िड
    0.37
    ären
    0.37
    ण्
    0.37
    POSITIVE LOGITS
     admittedly
    0.51
     tehát
    0.51
     Admittedly
    0.50
     genuinely
    0.49
     truly
    0.46
    所以
    0.46
     വിമ
    0.44
     arguably
    0.43
     Advertising
    0.43
     honestly
    0.43
    Act Density 0.027%

    No Known Activations