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

    Neuronpedia

    INDEX
    Explanations

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     promoting
    -0.07
    .output
    -0.07
     Tibetan
    -0.07
    اخر
    -0.06
    methods
    -0.06
    window
    -0.06
     xbox
    -0.06
     Moderator
    -0.06
     lacking
    -0.06
     TLS
    -0.06
    POSITIVE LOGITS
    ины
    0.06
    acos
    0.06
     放
    0.06
     Sup
    0.05
     knex
    0.05
     následující
    0.05
    تز
    0.05
    derive
    0.05
    нув
    0.05
     Postal
    0.05
    Act Density 0.006%

    No Known Activations