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

    Neuronpedia

    INDEX
    Explanations

    best practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     than
    0.48
    Welcome
    0.42
    razier
    0.42
    than
    0.42
    Prefer
    0.40
    jitter
    0.40
    formed
    0.38
    amu
    0.38
    Pref
    0.38
    Than
    0.38
    POSITIVE LOGITS
     Best
    0.84
     practices
    0.82
     Practices
    0.74
     बेस्ट
    0.74
     best
    0.73
    Best
    0.70
    practices
    0.62
    BEST
    0.62
     pratiques
    0.59
    best
    0.57
    Act Density 0.020%

    No Known Activations