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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    итися
    -0.06
     estilo
    -0.06
     kalk
    -0.06
    る
    -0.06
     uz
    -0.06
     Prosper
    -0.05
     Рос
    -0.05
     Belmont
    -0.05
     Rise
    -0.05
    fetch
    -0.05
    POSITIVE LOGITS
     zajím
    0.07
    ([[
    0.07
    θ
    0.07
     مثل
    0.07
    _const
    0.06
     motorcycles
    0.06
     사실
    0.06
    Ξ
    0.06
    Es
    0.06
     Repo
    0.06
    Act Density 0.096%

    No Known Activations