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

    Neuronpedia

    INDEX
    Explanations

    sigma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    caling
    -0.07
     backlog
    -0.07
     matches
    -0.07
     Brook
    -0.07
    894
    -0.06
     relate
    -0.06
    Hel
    -0.06
     awaken
    -0.06
    -capital
    -0.06
     eb
    -0.06
    POSITIVE LOGITS
    sigma
    0.13
     Sigma
    0.12
     σ
    0.10
    Sigma
    0.10
     sigma
    0.08
    ieve
    0.08
     Davidson
    0.08
    igma
    0.08
     Σ
    0.08
    (sigma
    0.07
    Act Density 0.003%

    No Known Activations