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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ži
    -0.07
     hiding
    -0.07
    NW
    -0.06
    じ
    -0.06
    δή
    -0.06
     неб
    -0.06
     december
    -0.06
    embrance
    -0.06
    thus
    -0.06
     molding
    -0.06
    POSITIVE LOGITS
    aret
    0.07
    alers
    0.07
    ○
    0.07
    riters
    0.06
    canonical
    0.06
    ordinates
    0.06
    (PDO
    0.06
    _staff
    0.06
    _pat
    0.06
    .op
    0.06
    Act Density 0.016%

    No Known Activations