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

    Neuronpedia

    INDEX
    Explanations

    sea, ships, boats, and ports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    o
    0.68
    in
    0.66
    e
    0.65
    .,
    0.62
    ado
    0.61
    á
    0.59
    ami
    0.57
    viving
    0.57
    ana
    0.57
     हिस्से
    0.57
    POSITIVE LOGITS
     boat
    1.38
    船
    1.34
     boats
    1.25
     maritime
    1.25
     deniz
    1.21
     ship
    1.20
     sea
    1.17
     кораб
    1.16
     ferry
    1.16
     sailboat
    1.16
    Act Density 0.308%

    No Known Activations