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

    Neuronpedia

    INDEX
    Explanations

    Mapping and transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intrigued
    -0.06
     Hue
    -0.06
    �
    -0.06
    ΜΠ
    -0.06
    Архів
    -0.06
    Concrete
    -0.06
     Sexo
    -0.06
    Spatial
    -0.06
    .base
    -0.06
     Pricing
    -0.05
    POSITIVE LOGITS
    ROM
    0.07
    -Series
    0.06
    _agg
    0.06
    izard
    0.06
     ABC
    0.06
     }()↵
    0.06
    .actor
    0.06
    ，则
    0.06
    ीप
    0.06
    .Profile
    0.06
    Act Density 0.016%

    No Known Activations