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

    Neuronpedia

    INDEX
    Explanations

    Mixed text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     граду
    -0.07
     hits
    -0.06
     conduct
    -0.06
    	j
    -0.06
     thou
    -0.06
    ียนบ
    -0.06
     Cove
    -0.06
     EDGE
    -0.06
     گ
    -0.06
    CADE
    -0.06
    POSITIVE LOGITS
    ?<
    0.07
    Dies
    0.06
    Arr
    0.06
    政治
    0.06
    .sql
    0.06
    意义
    0.06
     lớp
    0.06
     Erica
    0.06
     Principle
    0.06
    )^
    0.06
    Act Density 0.000%

    No Known Activations