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

    Neuronpedia

    INDEX
    Explanations

    industry, therapist, types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stray
    0.99
     ♦
    0.97
     Theo
    0.90
     ◆
    0.90
     Tat
    0.90
     PVA
    0.90
     ✔
    0.89
     theo
    0.88
     (_
    0.88
     Dia
    0.87
    POSITIVE LOGITS
    =
    1.88
    =-
    1.38
    }=
    1.20
    |=
    1.18
    =*
    1.18
    +
    1.17
    &=
    1.17
    +=
    1.14
    =(-
    1.13
    '=
    1.12
    Act Density 0.221%

    No Known Activations