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

    Neuronpedia

    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cole
    -0.06
     ascent
    -0.06
    -Un
    -0.06
    Sep
    -0.06
    Equip
    -0.06
    ван
    -0.06
     delivered
    -0.05
    .WebControls
    -0.05
    selling
    -0.05
     facts
    -0.05
    POSITIVE LOGITS
     temiz
    0.07
    .parents
    0.07
     вір
    0.07
    ./
    0.07
     данны
    0.06
    .Connect
    0.06
    累
    0.06
     infinit
    0.06
     vỏ
    0.06
     initiative
    0.06
    Act Density 0.005%

    No Known Activations