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

    Neuronpedia

    INDEX
    Explanations

    demonstrates aptitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legumes
    0.52
     megal
    0.49
     Bever
    0.49
     kem
    0.49
     ekonomik
    0.48
     preposition
    0.47
     peppermint
    0.46
     toxicants
    0.46
     raced
    0.46
     ital
    0.46
    POSITIVE LOGITS
    数据
    0.44
    Controller
    0.43
    Left
    0.42
    فير
    0.42
    كذا
    0.42
    层面
    0.41
    sigma
    0.41
    Parcel
    0.41
    п
    0.41
    Q
    0.41
    Act Density 0.001%

    No Known Activations