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

    Neuronpedia

    INDEX
    Explanations

    caches

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dunn
    -0.07
    ">×</
    -0.07
     Gon
    -0.07
    ضان
    -0.07
     Hiện
    -0.07
    owi
    -0.06
     Xu
    -0.06
     보면
    -0.06
     alles
    -0.06
    UnderTest
    -0.06
    POSITIVE LOGITS
     legit
    0.07
     intrinsic
    0.06
    pun
    0.06
     supernatural
    0.06
     managerial
    0.06
     embedding
    0.06
    _ENT
    0.06
     kvinner
    0.06
     concent
    0.06
     horizontally
    0.06
    Act Density 0.081%

    No Known Activations