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

    Neuronpedia

    INDEX
    Explanations

    latent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hugs
    -0.08
     Abdul
    -0.08
     towing
    -0.08
     comércio
    -0.08
     punching
    -0.08
     qualifying
    -0.08
     pled
    -0.08
     Screens
    -0.08
    HTMLElement
    -0.08
     benches
    -0.08
    POSITIVE LOGITS
     Bayesian
    0.14
     likelihood
    0.12
    ikelihood
    0.12
    _probs
    0.12
     probabilities
    0.11
     posterior
    0.11
    Likelihood
    0.11
     inference
    0.10
     probs
    0.10
    Inference
    0.10
    Act Density 0.010%

    No Known Activations