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

    Neuronpedia

    INDEX
    Explanations

    pants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pod
    -0.07
     Німеч
    -0.07
    _proof
    -0.07
    辑
    -0.06
    roups
    -0.06
     يوليو
    -0.06
    .direct
    -0.06
    ąd
    -0.06
    BTN
    -0.06
    uvre
    -0.06
    POSITIVE LOGITS
    ,v
    0.06
     flesh
    0.06
    іш
    0.06
    ежду
    0.06
     intric
    0.06
     recount
    0.06
    Declaration
    0.06
     introductory
    0.06
    Figure
    0.06
     Pennsylvania
    0.06
    Act Density 0.004%

    No Known Activations