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

    Neuronpedia

    INDEX
    Explanations

    patents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     זמן
    -0.07
     receptions
    -0.07
     civilized
    -0.07
    сложн
    -0.07
    徽
    -0.07
     Körper
    -0.06
     Farmer
    -0.06
    Taken
    -0.06
    markt
    -0.06
    .Diff
    -0.06
    POSITIVE LOGITS
    蒡
    0.08
    替
    0.07
    лив
    0.07
    альных
    0.06
     Jane
    0.06
    ㎐
    0.06
    チ
    0.06
    /red
    0.06
    ير
    0.06
    /load
    0.06
    Act Density 0.011%

    No Known Activations