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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pert
    -0.07
     ANY
    -0.07
    .**************↵
    -0.06
     pert
    -0.06
    hdl
    -0.06
    早
    -0.06
     ов
    -0.06
     penetrate
    -0.06
    Propagation
    -0.06
    cherche
    -0.06
    POSITIVE LOGITS
    �
    0.07
    不好
    0.06
     نصب
    0.06
     Shard
    0.06
     aussi
    0.06
     doub
    0.06
    _walk
    0.06
    .findById
    0.06
     خم
    0.06
     truly
    0.06
    Act Density 0.072%

    No Known Activations