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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     понима
    -0.07
     eigenen
    -0.07
     hoc
    -0.07
     nivel
    -0.06
    /right
    -0.06
     equally
    -0.06
     totally
    -0.06
     geile
    -0.06
     finally
    -0.06
     orient
    -0.06
    POSITIVE LOGITS
    ũi
    0.06
    323
    0.06
    .Hide
    0.06
    xef
    0.06
     researched
    0.06
     imperfect
    0.06
    γγραφ
    0.06
    -rating
    0.06
    撃
    0.06
    .deserialize
    0.06
    Act Density 0.162%

    No Known Activations