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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and code assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     archivo
    0.43
     COLORS
    0.43
     Libr
    0.42
     botanical
    0.41
     avert
    0.40
     files
    0.40
    Botan
    0.40
    ເລັກ
    0.39
     abrigo
    0.39
     shelves
    0.39
    POSITIVE LOGITS
    ို
    0.54
    state
    0.51
    mediaDevices
    0.48
    xtures
    0.47
    was
    0.46
    তই
    0.46
    イヤ
    0.46
    زیز
    0.46
    ージェ
    0.46
    isure
    0.44
    Act Density 0.003%

    No Known Activations