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

    Neuronpedia

    INDEX
    Explanations

    actions and advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wären
    0.34
    也被
    0.33
     waren
    0.32
     edilen
    0.32
     playerData
    0.30
     سننے
    0.29
     ซึ่ง
    0.29
     కారణంగా
    0.29
     hemos
    0.28
     kendisine
    0.28
    POSITIVE LOGITS
     hãy
    0.60
     make
    0.57
     use
    0.55
     try
    0.52
     постара
    0.52
     Make
    0.52
     jangan
    0.52
     take
    0.50
     keep
    0.49
     apply
    0.49
    Act Density 1.110%

    No Known Activations