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

    Neuronpedia

    INDEX
    Explanations

    research ethics and consent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Можно
    -0.07
    ספו
    -0.07
    抹
    -0.07
     Мос
    -0.07
     jpg
    -0.07
    Ground
    -0.06
    有幸
    -0.06
    莜
    -0.06
    eature
    -0.06
    lexical
    -0.06
    POSITIVE LOGITS
    0.08
     assay
    0.07
     Houston
    0.07
     Principal
    0.07
    した
    0.07
    🤖
    0.07
    ën
    0.07
     primaryKey
    0.07
    0.07
    0.07
    Act Density 0.005%

    No Known Activations