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

    Neuronpedia

    INDEX
    Explanations

    operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रवृत्ति
    0.40
     punishment
    0.39
     compressibility
    0.39
     elaboration
    0.38
     stars
    0.38
     earthquakes
    0.38
     delicacy
    0.38
     principle
    0.37
     monarchs
    0.37
     kings
    0.37
    POSITIVE LOGITS
     processes
    1.88
    processes
    1.84
     workflows
    1.80
    Processes
    1.79
     Processes
    1.77
     procedures
    1.66
     процессов
    1.65
     procesos
    1.63
     processos
    1.60
    workflows
    1.57
    Act Density 0.105%

    No Known Activations