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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.58
    RetentionPolicy
    -0.55
     Pender
    -0.54
     censiti
    -0.52
    didSet
    -0.52
    amatan
    -0.51
     CURLOPT
    -0.50
     Roskov
    -0.49
     înd
    -0.49
    AddTagHelper
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.60
     nahilalakip
    0.52
    ########.
    0.52
    曖昧さ回避
    0.50
    exitRule
    0.50
     betweenstory
    0.50
    AnchorStyles
    0.49
    expandindo
    0.49
    
    0.48
    Nya
    0.48
    Act Density 0.001%

    No Known Activations