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

    Neuronpedia

    INDEX
    Explanations

    makes or causes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mang
    0.36
     NAT
    0.36
     රට
    0.34
     Uniform
    0.34
     डेवलपमेंट
    0.34
     বিরুদ্ধে
    0.33
     Menlo
    0.33
     wabarakatuh
    0.33
     ইন
    0.33
     Ment
    0.33
    POSITIVE LOGITS
     makes
    2.05
    Makes
    1.98
     membuatnya
    1.95
    makes
    1.93
     Makes
    1.89
     يجعل
    1.89
     menjadikan
    1.88
    ทำให้
    1.87
     جعل
    1.71
    使得
    1.70
    Act Density 0.019%

    No Known Activations