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

    Neuronpedia

    INDEX
    Explanations

    code/logic guarantees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sthrough
    -0.06
    bff
    -0.06
    itory
    -0.06
     определить
    -0.06
     Entertainment
    -0.06
     حول
    -0.06
    Seq
    -0.06
     expecting
    -0.06
    lever
    -0.06
    TOTAL
    -0.06
    POSITIVE LOGITS
     vibrant
    0.06
     近
    0.06
     royalties
    0.06
    GIS
    0.06
    _dict
    0.06
     Ho
    0.06
    	n
    0.06
    <<(
    0.06
    ……。
    0.06
    (Parse
    0.06
    Act Density 0.198%

    No Known Activations