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

    Neuronpedia

    INDEX
    Explanations

    displacement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .hs
    -0.07
     pastors
    -0.07
     nø
    -0.07
     terrace
    -0.07
     furnished
    -0.07
     OR
    -0.07
     Ser
    -0.06
     Roo
    -0.06
     appearing
    -0.06
    arehouse
    -0.06
    POSITIVE LOGITS
     displacement
    0.13
     displaced
    0.12
     displ
    0.09
    placement
    0.09
    placing
    0.08
     loại
    0.07
    ipples
    0.07
    ंद
    0.07
    =device
    0.07
    deniz
    0.06
    Act Density 0.005%

    No Known Activations