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

    Neuronpedia

    INDEX
    Explanations

    research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COUNTY
    -0.07
     Squadron
    -0.07
     fatal
    -0.07
     melanch
    -0.07
    歲
    -0.06
     County
    -0.06
    Cou
    -0.06
    CreateTime
    -0.06
     Employ
    -0.06
     Documentary
    -0.06
    POSITIVE LOGITS
    可能性
    0.08
     выяв
    0.06
    692
    0.06
    classified
    0.06
     neler
    0.06
     første
    0.06
    ==$
    0.06
     nesting
    0.06
    成立
    0.06
    emez
    0.06
    Act Density 0.041%

    No Known Activations