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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xFF
    -0.07
    Spawn
    -0.07
    兰
    -0.07
    进一步
    -0.06
    ění
    -0.06
     Lam
    -0.06
     Wolverine
    -0.06
    .Var
    -0.06
    .Tab
    -0.06
     INC
    -0.06
    POSITIVE LOGITS
     oldu
    0.07
    Understanding
    0.06
     kann
    0.06
    ework
    0.06
     Hlav
    0.06
     confidently
    0.06
     bootloader
    0.06
     installed
    0.06
     hade
    0.06
    "",
    0.06
    Act Density 0.089%

    No Known Activations