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

    Neuronpedia

    INDEX
    Explanations

    based

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frames
    -0.07
    (u
    -0.07
    _cached
    -0.07
     cpu
    -0.06
     hn
    -0.06
    (mt
    -0.06
     U
    -0.06
    itch
    -0.06
    dain
    -0.06
    키
    -0.06
    POSITIVE LOGITS
    -original
    0.06
    ibilities
    0.06
     expanding
    0.06
    ated
    0.06
     opět
    0.06
    .desktop
    0.06
     maç
    0.06
    osed
    0.06
     concerning
    0.06
    _mag
    0.06
    Act Density 0.053%

    No Known Activations