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

    Neuronpedia

    INDEX
    Explanations

    like this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
        
    0.45
     Such
    0.43
     Latest
    0.41
            
    0.40
       
    0.39
     etc
    0.38
     Whatever
    0.38
     Otherwise
    0.37
     Places
    0.36
    ↵
    0.36
    POSITIVE LOGITS
     څنګه
    0.68
     ours
    0.56
     unto
    0.53
     those
    0.52
     будто
    0.51
     minded
    0.48
     yours
    0.45
     how
    0.44
    对待
    0.44
    平常
    0.43
    Act Density 0.092%

    No Known Activations