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

    Neuronpedia

    INDEX
    Explanations

    code elements and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     getAll
    0.95
    )==
    0.94
    ==
    0.92
    )</
    0.92
     getValue
    0.85
     tạo
    0.84
    =
    0.84
    为
    0.84
    =="
    0.83
     getting
    0.83
    POSITIVE LOGITS
     inoltre
    0.68
    also
    0.67
    Also
    0.64
     -=
    0.64
     |=
    0.61
    ijų
    0.61
    consulté
    0.61
     &=
    0.59
    zier
    0.59
     ፡፡
    0.59
    Act Density 0.215%

    No Known Activations