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

    Neuronpedia

    INDEX
    Explanations

    Online chat excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ключ
    -0.07
    345
    -0.06
    خاص
    -0.06
    :'↵
    -0.06
    …I
    -0.06
     Himself
    -0.06
     Hait
    -0.06
    .Tipo
    -0.06
     �
    -0.06
    stash
    -0.06
    POSITIVE LOGITS
     ◄
    0.07
    ")),↵
    0.07
     berg
    0.07
     eser
    0.07
     sink
    0.06
    技能
    0.06
    �
    0.06
     Ş
    0.06
     participant
    0.06
     Jewel
    0.06
    Act Density 0.027%

    No Known Activations