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

    Neuronpedia

    INDEX
    Explanations

    making *you* feel they understand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intentions
    0.43
     instructors
    0.41
     emas
    0.41
     enzymes
    0.39
     advancements
    0.39
    파트
    0.39
     intents
    0.39
     insecticides
    0.39
     exosomes
    0.38
    انة
    0.38
    POSITIVE LOGITS
    美好
    0.50
    şi
    0.46
    喑
    0.43
    ἡ
    0.40
    曈
    0.40
     रो
    0.40
    哏
    0.39
    STON
    0.39
    䫒
    0.39
     नेतृत्व
    0.38
    Act Density 0.000%

    No Known Activations