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

    Neuronpedia

    INDEX
    Explanations

    no condition or item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.49
     nejen
    0.47
     And
    0.43
     וע
    0.43
     মতোই
    0.42
     และ
    0.41
     snd
    0.40
    autogui
    0.40
     radiographs
    0.40
    fp
    0.39
    POSITIVE LOGITS
     ninguno
    0.56
    敢
    0.54
     siquiera
    0.53
    None
    0.53
    Nobody
    0.52
     nessuno
    0.51
     ninguna
    0.50
     هیچ
    0.50
     alcun
    0.49
     whatsoever
    0.49
    Act Density 0.060%

    No Known Activations