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

    Neuronpedia

    INDEX
    Explanations

    marketing efficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    μού
    0.57
     gstlal
    0.53
     Ettha
    0.50
    ಕರಣ
    0.50
     labbhati
    0.49
     材質
    0.49
    뎃
    0.47
    ্লিকেশন
    0.46
     کمپنیوں
    0.46
     कंपनियां
    0.46
    POSITIVE LOGITS
    T
    0.64
    O
    0.56
      
    0.52
     John
    0.52
    G
    0.51
     helpful
    0.50
    í
    0.50
     new
    0.50
    S
    0.49
    R
    0.49
    Act Density 0.001%

    No Known Activations