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

    Neuronpedia

    INDEX
    Explanations

    Requirements and constraints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Avril
    -0.09
     sarcas
    -0.08
     depreci
    -0.08
     Tablet
    -0.08
    Tablet
    -0.08
     depreciation
    -0.08
     Mystery
    -0.08
     deceptive
    -0.08
     abbrevi
    -0.08
     consoles
    -0.08
    POSITIVE LOGITS
    Desired
    0.11
    Fortunately
    0.11
    Luckily
    0.10
     подобрать
    0.10
    desired
    0.10
     Fortunately
    0.10
     Desired
    0.10
     chosen
    0.10
     desired
    0.10
    chosen
    0.09
    Act Density 0.045%

    No Known Activations