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

    Neuronpedia

    INDEX
    Explanations

    technical commands and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    っき
    0.58
     majority
    0.54
    arent
    0.52
     higher
    0.51
     highest
    0.50
    uest
    0.48
     pure
    0.48
    impossible
    0.47
    equipment
    0.46
      
    0.45
    POSITIVE LOGITS
     japanese
    1.07
    বৃত্তি
    1.06
     ಬಿಜೆ
    1.04
     Ме
    1.02
    onRouteChange
    1.01
     sfai
    0.99
     nltk
    0.99
     東
    0.99
    განიზ
    0.98
    ಜ್
    0.98
    Act Density 1.063%

    No Known Activations