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

    Neuronpedia

    INDEX
    Explanations

    unfolds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Elements
    -0.07
    ryptography
    -0.06
     restructuring
    -0.06
     cardboard
    -0.06
    tty
    -0.06
     rolls
    -0.06
    umat
    -0.06
    positor
    -0.06
     jou
    -0.06
    (can
    -0.06
    POSITIVE LOGITS
     nause
    0.07
    ुत
    0.07
     حمل
    0.07
     Movement
    0.07
     Syria
    0.06
    weet
    0.06
     hệ
    0.06
    rock
    0.06
     ROAD
    0.06
    ount
    0.06
    Act Density 1.067%

    No Known Activations