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

    Neuronpedia

    INDEX
    Explanations

    domain followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ból
    0.44
    ב
    0.41
     submanifold
    0.40
     glPushMatrix
    0.40
     thalassemia
    0.40
     dominions
    0.39
     четы
    0.39
    mData
    0.38
     গম্ভীর
    0.38
     LMFBR
    0.37
    POSITIVE LOGITS
    :
    0.71
    7
    0.69
    8
    0.67
    9
    0.65
    5
    0.63
    6
    0.61
    4
    0.53
    ING
    0.51
    ]
    0.50
    ).
    0.49
    Act Density 0.961%

    No Known Activations