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

    Neuronpedia

    INDEX
    Explanations

    it, there, or this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     driven
    0.23
     initializes
    0.22
     achieves
    0.22
     incorporates
    0.22
     interwoven
    0.22
     generates
    0.21
     connects
    0.21
     illuminates
    0.21
     extends
    0.21
     begins
    0.21
    POSITIVE LOGITS
     это
    0.33
    there
    0.32
     זה
    0.30
     there
    0.29
     đừng
    0.28
     it
    0.28
    इसमें
    0.27
    это
    0.27
     এটাই
    0.26
     chances
    0.26
    Act Density 0.070%

    No Known Activations