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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GeoNames
    -0.65
    enti
    -0.51
     Empieza
    -0.49
     consectetur
    -0.48
     CURIAM
    -0.47
    :✨
    -0.47
     CanadaChoose
    -0.46
    gogo
    -0.46
     linkovi
    -0.45
    vay
    -0.44
    POSITIVE LOGITS
     houſe
    0.63
     Monfieur
    0.61
     igång
    0.60
     Houſe
    0.60
     purpoſe
    0.59
     onBind
    0.59
    yntaxException
    0.58
     perſon
    0.58
     myſelf
    0.58
     ſta
    0.57
    Act Density 0.009%

    No Known Activations