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

    Neuronpedia

    INDEX
    Explanations

    Model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仅供
    -0.07
     họp
    -0.07
    혹
    -0.07
    getStore
    -0.06
    性和
    -0.06
    Veter
    -0.06
     misunderstood
    -0.06
     splits
    -0.06
     Election
    -0.06
    .deg
    -0.06
    POSITIVE LOGITS
     increase
    0.07
    (filePath
    0.07
    (chunk
    0.07
     human
    0.07
    Hip
    0.07
    低成本
    0.07
    _drop
    0.07
    𬭩
    0.07
    .label
    0.07
    멩
    0.06
    Act Density 0.001%

    No Known Activations