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

    Neuronpedia

    INDEX
    Explanations

    checking for existence or improvement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ू
    0.48
     풀
    0.48
     Möbius
    0.48
    涳
    0.46
     కల
    0.45
    相同的
    0.44
    uleiro
    0.44
     সেনা
    0.44
     রহ
    0.43
    는데
    0.43
    POSITIVE LOGITS
    are
    0.51
        
    0.50
     haga
    0.49
          
    0.48
     jes
    0.47
    use
    0.46
     metod
    0.46
     mill
    0.45
    Members
    0.45
     et
    0.45
    Act Density 0.000%

    No Known Activations