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

    Neuronpedia

    INDEX
    Explanations

    providing valuable insights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மனு
    0.47
    usting
    0.44
     సంవత్స
    0.44
    ភ្ជាប់
    0.43
    мата
    0.43
    ᚑ
    0.43
    Assuming
    0.42
    жон
    0.42
    捋
    0.42
    사항
    0.41
    POSITIVE LOGITS
     null
    0.49
     phosphates
    0.46
    phosphate
    0.45
     phosphate
    0.44
     phosphat
    0.43
     ml
    0.43
     ferro
    0.42
     mm
    0.42
     ferr
    0.42
     hot
    0.42
    Act Density 0.001%

    No Known Activations