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

    Neuronpedia

    INDEX
    Explanations

    files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ター
    -0.08
     ATTR
    -0.07
     unreal
    -0.07
     ഭ
    -0.07
     livre
    -0.07
     reports
    -0.07
    Evaluator
    -0.07
     targets
    -0.07
    LAS
    -0.07
    .Float
    -0.07
    POSITIVE LOGITS
    寻
    0.08
     پاتې
    0.08
    三级
    0.08
    .lifecycle
    0.08
     patrons
    0.08
     Harold
    0.08
     Movies
    0.08
    /Documents
    0.07
     MSD
    0.07
     innovate
    0.07
    Act Density 0.000%

    No Known Activations