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

    Neuronpedia

    INDEX
    Explanations

    numbered lists and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेलकम
    0.44
     midwives
    0.43
    වුන්
    0.38
     immunosupp
    0.38
    Bahn
    0.38
    Bau
    0.38
     infrastrukt
    0.38
    タウン
    0.37
     choroby
    0.37
    紥
    0.36
    POSITIVE LOGITS
     etc
    0.48
    $
    0.41
          
    0.40
    etc
    0.40
     тощо
    0.40
    甚至
    0.38
     和
    0.38
    })
    0.37
              
    0.37
    甚至是
    0.37
    Act Density 0.359%

    No Known Activations