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

    Neuronpedia

    INDEX
    Explanations

    learning, control, and estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    商标
    0.60
    税务
    0.60
    现代化
    0.57
    aurants
    0.55
     понадоби
    0.54
    旄
    0.54
    高志森
    0.54
    铁路
    0.54
    éraires
    0.54
     caractères
    0.53
    POSITIVE LOGITS
     update
    0.88
     learning
    0.85
     vectors
    0.81
     stochastic
    0.79
     Algorithm
    0.78
     perturbations
    0.77
     feedback
    0.76
     synthetic
    0.75
     perturb
    0.75
     probabilistic
    0.74
    Act Density 0.162%

    No Known Activations