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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Diss
    -0.07
     Brent
    -0.07
     fonts
    -0.07
     Yan
    -0.07
     Elevated
    -0.07
     chase
    -0.07
     Streams
    -0.07
     Fan
    -0.06
     Landscape
    -0.06
    prev
    -0.06
    POSITIVE LOGITS
     Hearth
    0.06
    ValueType
    0.06
    仲
    0.06
     misunderstand
    0.06
    二二二二
    0.06
    ABCDEFGHI
    0.06
    ，用
    0.06
    NegativeButton
    0.06
     вним
    0.06
     counsel
    0.06
    Act Density 0.007%

    No Known Activations