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

    Neuronpedia

    INDEX
    Explanations

    func New

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deten
    0.90
     bombas
    0.86
    ⤥
    0.86
    $;
    0.82
    rzym
    0.79
    kräfte
    0.76
     stimul
    0.76
     entreten
    0.76
     rubber
    0.76
     teste
    0.76
    POSITIVE LOGITS
     New
    1.08
    一个新的
    1.01
     Register
    0.85
     Handic
    0.85
     Multiply
    0.82
    New
    0.81
     Genre
    0.79
     Involvement
    0.79
    ција
    0.78
     новый
    0.78
    Act Density 0.007%

    No Known Activations