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

    Neuronpedia

    INDEX
    Explanations

    math and physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     För
    -0.07
    Navigator
    -0.07
     naked
    -0.06
    Vector
    -0.06
     Collapse
    -0.06
     economical
    -0.06
     Escape
    -0.06
    Mul
    -0.06
     있을
    -0.06
    (selected
    -0.06
    POSITIVE LOGITS
     pilgr
    0.06
    ่งข
    0.06
     subdiv
    0.06
     Jeremy
    0.06
    alarında
    0.06
    HEN
    0.06
     Kasich
    0.05
     sculpt
    0.05
    UILTIN
    0.05
     upset
    0.05
    Act Density 0.017%

    No Known Activations