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

    Neuronpedia

    INDEX
    Explanations

    frame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frame
    -0.80
     frame
    -0.77
     FRAME
    -0.77
    帖最后由
    -0.70
     betweenstory
    -0.68
     Frames
    -0.68
     BorderRadius
    -0.64
    frame
    -0.64
     frames
    -0.63
    MessageTagHelper
    -0.60
    POSITIVE LOGITS
    <bos>
    0.70
    roit
    0.50
     dés
    0.47
    utas
    0.46
    akes
    0.43
    ırı
    0.43
    EndInit
    0.42
     Oru
    0.41
    ufact
    0.41
    QMetaType
    0.41
    Act Density 0.077%

    No Known Activations