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

    Neuronpedia

    INDEX
    Explanations

    tip followed by advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trout
    0.50
     პროფილი
    0.47
    нд
    0.46
    സിന്
    0.45
    蹌
    0.43
    sembled
    0.43
    unis
    0.42
     რამდენ
    0.41
    ซีน
    0.41
    ﺬ
    0.41
    POSITIVE LOGITS
     tips
    0.63
    Tips
    0.63
    Tip
    0.60
    tips
    0.60
     Tips
    0.58
     Tip
    0.57
     tip
    0.55
    TIP
    0.55
    ER
    0.53
    tip
    0.52
    Act Density 0.001%

    No Known Activations