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

    Neuronpedia

    INDEX
    Explanations

    UI elements, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    電視
    -0.07
     Vz
    -0.07
    Wifi
    -0.06
     strongly
    -0.06
    .white
    -0.06
    елик
    -0.06
     broadcasters
    -0.06
     کیل
    -0.06
     باید
    -0.06
     shoes
    -0.06
    POSITIVE LOGITS
    "context
    0.07
     Teresa
    0.07
    ovenant
    0.06
    Am
    0.06
     Applied
    0.06
     Completed
    0.06
     Newfoundland
    0.06
    Clin
    0.06
    -auth
    0.06
     db
    0.06
    Act Density 0.050%

    No Known Activations