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

    Neuronpedia

    INDEX
    Explanations

    express middleware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miras
    1.48
    ்ட
    1.42
     Caw
    1.42
    োষ
    1.38
     Tuhan
    1.37
    计划
    1.36
     проект
    1.34
     progetto
    1.33
    ණ්
    1.30
    OutputFile
    1.29
    POSITIVE LOGITS
    गेशन
    1.47
    AsUp
    1.43
    offs
    1.30
    enzyme
    1.28
    вање
    1.27
     extra
    1.27
     ऑफ़
    1.24
    bies
    1.24
    മ്പോൾ
    1.22
    lemma
    1.22
    Act Density 0.000%

    No Known Activations