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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     that
    -1.79
    that
    -1.26
     bahwa
    -1.07
     rằng
    -0.98
     ότι
    -0.83
     того
    -0.82
     kwamba
    -0.82
     bahawa
    -0.81
     że
    -0.81
    That
    -0.78
    POSITIVE LOGITS
    PYX
    0.85
    rxjs
    0.60
     we
    0.56
     contributes
    0.54
    XmlRootElement
    0.54
     favours
    0.53
     <=",
    0.53
     arises
    0.52
     is
    0.52
     justifies
    0.51
    Act Density 0.277%

    No Known Activations