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

    Neuronpedia

    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.65
    gartner
    -0.53
    Források
    -0.53
    brink
    -0.50
     Game
    -0.44
    forRoot
    -0.43
    ttemberg
    -0.43
    ennung
    -0.43
    gway
    -0.43
    riwal
    -0.43
    POSITIVE LOGITS
    ftagPool
    0.82
    Diwedd
    0.68
    OpenHelper
    0.67
    
    0.61
    featureID
    0.60
    Espèce
    0.59
    WebControls
    0.57
    rowable
    0.56
    GEBURTS
    0.56
     дописавши
    0.55
    Act Density 0.040%

    No Known Activations