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

    Neuronpedia

    INDEX
    Explanations

    Dimensions and directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jpeg
    -0.08
     Iglesias
    -0.08
     ogl
    -0.08
    嫁
    -0.08
     almonds
    -0.08
     etree
    -0.08
     glitches
    -0.08
     epub
    -0.08
     हस्त
    -0.08
     walnuts
    -0.07
    POSITIVE LOGITS
     вперед
    0.13
     vorne
    0.11
    north
    0.11
     NORTH
    0.10
    (front
    0.10
    .forward
    0.10
     forward
    0.10
    _FORWARD
    0.10
     north
    0.10
     hinten
    0.09
    Act Density 0.021%

    No Known Activations