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

    Neuronpedia

    INDEX
    Explanations

    News articles and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.69
    SharedCtor
    -0.65
     debout
    -0.61
    Personensuche
    -0.58
     Administrativna
    -0.55
     hjemme
    -0.54
     pancreatitis
    -0.54
     referenties
    -0.54
    álogos
    -0.52
     verschil
    -0.51
    POSITIVE LOGITS
    didSet
    0.76
    TintMode
    0.64
    0.62
    Tembelea
    0.56
     مرئيه
    0.56
     ProtoMessage
    0.54
     createSlice
    0.52
    JNIEnv
    0.52
    IconModule
    0.51
    PasswordEncoder
    0.51
    Act Density 0.007%

    No Known Activations