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

    Neuronpedia

    INDEX
    Explanations

    the key to success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notable
    0.47
     noteworthy
    0.45
    эл
    0.42
    presumably
    0.42
    ondere
    0.41
     reprieve
    0.40
     Notable
    0.39
    orgt
    0.38
     குறிப்பிடத்தக்க
    0.38
    тельстве
    0.38
    POSITIVE LOGITS
     biggest
    0.87
    最重要的
    0.87
     greatest
    0.84
     secret
    0.80
     hardest
    0.77
     success
    0.75
     sooner
    0.74
    最好的
    0.73
     mantra
    0.73
     Importance
    0.73
    Act Density 0.030%

    No Known Activations