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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bindung
    -0.07
    wyn
    -0.06
    ortality
    -0.06
    Sampler
    -0.06
     virtue
    -0.06
     Laur
    -0.06
    XE
    -0.06
    )).
    -0.06
     subjective
    -0.06
    rtle
    -0.06
    POSITIVE LOGITS
    -mini
    0.07
     Silent
    0.07
    ="">↵
    0.07
    专业
    0.07
    .DropTable
    0.06
     yaklaşık
    0.06
    -Semitic
    0.06
    igne
    0.06
    .tencent
    0.06
    年的
    0.06
    Act Density 0.050%

    No Known Activations