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

    Neuronpedia

    INDEX
    Explanations

    which format or which is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    リーン
    0.46
    ya
    0.43
    '
    0.41
     tires
    0.40
    前
    0.40
    Does
    0.39
     washers
    0.39
    men
    0.39
    Sat
    0.39
    ORTS
    0.39
    POSITIVE LOGITS
     bolje
    0.48
     thriving
    0.46
    ứ
    0.46
     skepticism
    0.45
    蜚
    0.45
    contentType
    0.45
     శాఖ
    0.45
     विस्त
    0.44
     remboursement
    0.43
     conceptos
    0.43
    Act Density 0.003%

    No Known Activations