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

    Neuronpedia

    INDEX
    Explanations

    political succession

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    뿐
    0.51
    ěli
    0.44
     fenomeni
    0.44
    Bienvenidos
    0.44
    瘧
    0.43
    糁
    0.43
     गड्
    0.43
     Clustering
    0.43
    谗
    0.43
    碜
    0.43
    POSITIVE LOGITS
     towards
    0.52
     ,
    0.49
     this
    0.47
     various
    0.46
     (
    0.45
     for
    0.44
     stores
    0.43
     is
    0.43
     out
    0.42
     .
    0.42
    Act Density 0.000%

    No Known Activations