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

    Neuronpedia

    INDEX
    Explanations

    aim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Movie
    -0.08
    laden
    -0.07
    Financial
    -0.07
    CTL
    -0.07
     movie
    -0.06
    /User
    -0.06
    memo
    -0.06
    liquid
    -0.06
     Bonds
    -0.06
    .Left
    -0.06
    POSITIVE LOGITS
    алист
    0.07
    暖
    0.06
     treffen
    0.06
    。また
    0.06
    yš
    0.06
    DefaultCloseOperation
    0.06
    从
    0.06
     verschied
    0.06
     Assumes
    0.05
     небольш
    0.05
    Act Density 0.049%

    No Known Activations