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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    据报道
    -0.07
    NotNil
    -0.07
     debe
    -0.07
    ...(
    -0.07
     flux
    -0.06
    들이
    -0.06
    日至
    -0.06
    mean
    -0.06
    installed
    -0.06
    mode
    -0.06
    POSITIVE LOGITS
    品牌形象
    0.07
     الرحمن
    0.07
    ondheim
    0.07
     Orchard
    0.07
     unrelated
    0.07
     Premiership
    0.07
     amore
    0.06
    龙头企业
    0.06
    _similarity
    0.06
    _
↵
↵
    0.06
    Act Density 0.004%

    No Known Activations