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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orphic
    -0.06
    .null
    -0.06
    ži
    -0.06
    ável
    -0.06
    _Menu
    -0.06
     zach
    -0.06
     finalist
    -0.06
     Rei
    -0.06
     Computer
    -0.06
    альным
    -0.06
    POSITIVE LOGITS
     withhold
    0.07
     Wing
    0.07
     DL
    0.07
     SW
    0.06
     perks
    0.06
    문화
    0.06
     conditioner
    0.06
    fortawesome
    0.06
     Fairfax
    0.06
    植
    0.06
    Act Density 0.000%

    No Known Activations