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

    Neuronpedia

    INDEX
    Explanations

    Afghanistan, "Vi", and "Bri"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vi
    -0.75
     disambiguazione
    -0.73
     Ri
    -0.70
     Bri
    -0.67
    Ri
    -0.66
    messageInfo
    -0.66
     ResourceManager
    -0.63
    findpost
    -0.63
     ModelExpression
    -0.62
     Normdatei
    -0.59
    POSITIVE LOGITS
     quæ
    0.66
     Theſe
    0.64
     Monfieur
    0.63
    cluye
    0.62
    ſelves
    0.61
     himſelf
    0.60
     themſelves
    0.60
     itſelf
    0.57
     myſelf
    0.57
    ſelf
    0.56
    Act Density 2.006%

    No Known Activations