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

    Neuronpedia

    INDEX
    Explanations

    safe drug use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ='${
    -0.07
    اجع
    -0.07
     자료
    -0.07
    ováním
    -0.06
    .LENGTH
    -0.06
    .FETCH
    -0.06
    _SCALE
    -0.06
     readers
    -0.06
     İşte
    -0.06
     fkk
    -0.06
    POSITIVE LOGITS
     Sparse
    0.07
     surrender
    0.07
     ech
    0.06
    (Rect
    0.06
     ступ
    0.06
     discovering
    0.06
    elix
    0.06
    apus
    0.06
    束
    0.06
     Crowley
    0.06
    Act Density 0.008%

    No Known Activations