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

    Neuronpedia

    INDEX
    Explanations

    edges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hale
    -0.08
     optical
    -0.07
     responsibly
    -0.07
     藤
    -0.07
    cuda
    -0.06
    deck
    -0.06
    upos
    -0.06
    appa
    -0.06
     dever
    -0.06
    entre
    -0.06
    POSITIVE LOGITS
    च
    0.07
    }<
    0.06
    .XRTableCell
    0.06
    사람
    0.06
    .mob
    0.06
    .relative
    0.06
     Vic
    0.06
     Rip
    0.06
    _lifetime
    0.06
     Auswahl
    0.06
    Act Density 0.035%

    No Known Activations