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

    Neuronpedia

    INDEX
    Explanations

    advice and implicit rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    description
    0.85
     สืบค้น
    0.80
    Description
    0.78
     Description
    0.78
    满足
    0.76
    ುತ್ತದೆ
    0.75
     description
    0.74
    summary
    0.74
     बकाया
    0.73
     заинтересо
    0.73
    POSITIVE LOGITS
     advice
    3.46
     Advice
    3.11
     advise
    2.82
    Advice
    2.80
    advice
    2.78
     advises
    2.65
     advices
    2.64
     consejos
    2.50
     советы
    2.50
     advising
    2.48
    Act Density 0.289%

    No Known Activations