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

    Neuronpedia

    INDEX
    Explanations

    project phases

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     автоматически
    0.54
     indiscrimin
    0.53
    规律
    0.49
     indiscriminate
    0.49
    Automatically
    0.48
     sukham
    0.47
     natürliche
    0.47
    stärke
    0.47
     disob
    0.46
    пуляр
    0.46
    POSITIVE LOGITS
     phases
    1.60
     Phase
    1.55
     development
    1.52
     prototyping
    1.51
     phase
    1.50
    Phase
    1.48
     prototype
    1.46
     Phases
    1.42
     deliverables
    1.41
     milestones
    1.40
    Act Density 1.339%

    No Known Activations