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

    Neuronpedia

    INDEX
    Explanations

    Submarines and naval ships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    combo
    -0.07
    centage
    -0.06
    _put
    -0.06
     العام
    -0.06
    _rev
    -0.06
    یست
    -0.06
    _identity
    -0.06
    يج
    -0.06
    cef
    -0.06
    ựa
    -0.06
    POSITIVE LOGITS
    837
    0.07
    姐
    0.06
     جل
    0.06
    905
    0.06
    Washington
    0.06
     Washington
    0.06
     AHL
    0.06
     curtains
    0.06
     yapım
    0.06
    uesta
    0.06
    Act Density 0.026%

    No Known Activations