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

    Neuronpedia

    INDEX
    Explanations

    business strategy concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.59
    are
    0.52
     Statist
    0.49
     cramps
    0.46
    izare
    0.45
    ä
    0.45
    such
    0.44
    éor
    0.44
    anny
    0.44
    DEFGHIJKLMNOP
    0.44
    POSITIVE LOGITS
    ٥
    0.58
    ૫
    0.55
    ５
    0.54
    ち
    0.49
     टीमों
    0.49
    Результа
    0.49
    時の
    0.47
     МА
    0.47
    5
    0.47
     इसका
    0.46
    Act Density 0.452%

    No Known Activations