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

    Neuronpedia

    INDEX
    Explanations

    URLs and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.63
    4
    0.54
    3
    0.52
    ，
    0.51
    7
    0.47
     open
    0.45
    5
    0.45
     (
    0.45
    Open
    0.44
    2
    0.44
    POSITIVE LOGITS
    isseurs
    0.48
     pabbaj
    0.47
    lhe
    0.46
     consiste
    0.44
     кеңселер
    0.44
    통산
    0.43
     veuillez
    0.42
     ಇತರ
    0.42
     veineux
    0.42
    íss
    0.42
    Act Density 0.001%

    No Known Activations