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

    Neuronpedia

    INDEX
    Explanations

    Eco, Star

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mág
    -0.08
     क्यों
    -0.08
    踩
    -0.07
     Joining
    -0.07
     Integrity
    -0.07
     Security
    -0.07
     Raised
    -0.07
    ечение
    -0.07
    _confirmation
    -0.07
     Problems
    -0.07
    POSITIVE LOGITS
    catalog
    0.08
    ila
    0.08
     benchmarking
    0.08
     benchmark
    0.08
     catalogue
    0.08
     allocating
    0.07
    fia
    0.07
    calcul
    0.07
     redesigned
    0.07
     bibli
    0.07
    Act Density 0.006%

    No Known Activations