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

    Neuronpedia

    INDEX
    Explanations

    dispute resolution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Representative
    -0.07
    ℃
    -0.07
     Dep
    -0.07
    特征
    -0.07
     Foundations
    -0.06
    (Menu
    -0.06
    .Tab
    -0.06
     evacuation
    -0.06
     FY
    -0.06
    ManagedObjectContext
    -0.06
    POSITIVE LOGITS
    拿起
    0.08
    Mirror
    0.08
    戴上
    0.07
     LIABILITY
    0.07
    纫
    0.07
    淠
    0.07
    Broken
    0.07
    ]!=
    0.07
    done
    0.07
     cuckold
    0.07
    Act Density 0.012%

    No Known Activations