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

    Neuronpedia

    INDEX
    Explanations

    values and other things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =")
    0.51
    情報の
    0.47
    ósitos
    0.47
    akkhati
    0.47
     demás
    0.45
     গ্রস্থ
    0.45
    ﻂ
    0.45
    ➸
    0.45
    0.45
    ु
    0.44
    POSITIVE LOGITS
     was
    0.58
     än
    0.55
     kon
    0.54
     and
    0.53
     pas
    0.53
     la
    0.52
     k
    0.51
     sub
    0.51
     av
    0.50
     had
    0.49
    Act Density 0.000%

    No Known Activations