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

    Neuronpedia

    INDEX
    Explanations

    About us/contact us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Us
    -0.66
     Sam
    -0.63
     Signalez
    -0.58
     Fr
    -0.55
     Sad
    -0.52
     fre
    -0.52
    nok
    -0.52
     U
    -0.52
     Sis
    -0.52
     Bro
    -0.51
    POSITIVE LOGITS
    aarrggbb
    0.66
     newBuilder
    0.64
     sherds
    0.63
     titolata
    0.63
     Etrus
    0.62
     quæ
    0.61
    IGraphics
    0.60
     sulph
    0.60
     الحره
    0.60
     hausse
    0.60
    Act Density 1.038%

    No Known Activations