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

    Neuronpedia

    INDEX
    Explanations

    advice, mistakes, or challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     निर्दिष्ट
    0.84
    stantially
    0.80
     accordance
    0.78
     specified
    0.77
     substantially
    0.77
     suitably
    0.76
     correspondingly
    0.76
    specified
    0.75
     appreciably
    0.74
    ována
    0.73
    POSITIVE LOGITS
     Tips
    1.83
     misconceptions
    1.81
     Mistakes
    1.81
     Tipps
    1.76
     tips
    1.72
     mistakes
    1.71
     pitfalls
    1.67
    Tips
    1.65
     consejos
    1.57
     challenges
    1.56
    Act Density 0.276%

    No Known Activations